Eval: Cardinal Directions #1060
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
dbautista1
requested review from
andrew-openai,
jwang47,
logankilpatrick and
rlbayes
as code owners
usama-openai
approved these changes
Jun 1, 2023
Collaborator
usama-openai
left a comment
usama-openai
left a comment
There was a problem hiding this comment.
Thanks for submitting this eval! This PR looks good. I'm approving this PR.
Collaborator
|
You should see GPT-4 API access enabled in your account in the next few days. |
Contributor
Author
|
Thanks @usama-openai, I'm really glad I can contribute. I'm still working on improving the whole of the previous PR Relative Orientations (#1000 )which this one was based on. By the time I'm finished improving the prompt and as well as the questions, I intend to be able to provide an answer key with diagrams which could help verify ideals during review. Then if necessary we could discuss pruning and merging samples from that PR with this one or vice versa. It's been a busy week but I'm trying to prepare it for you guys as soon as possible. Kind regards. |
13 tasks
andrew-openai
pushed a commit
that referenced
this pull request
Jun 7, 2023
# Thank you for contributing an eval!♥️ 🚨 Please make sure your PR follows these guidelines, **failure to follow the guidelines below will result in the PR being closed automatically**. Note that even if the criteria are met, that does not guarantee the PR will be merged nor GPT-4 access be granted. 🚨 **PLEASE READ THIS**: In order for a PR to be merged, it must fail on GPT-4. We are aware that right now, users do not have access, so you will not be able to tell if the eval fails or not. Please run your eval with GPT-3.5-Turbo, but keep in mind as we run the eval, if GPT-4 gets higher than 90% on the eval, we will likely reject it since GPT-4 is already capable of completing the task. We plan to roll out a way for users submitting evals to see the eval performance on GPT-4 soon. Stay tuned! Until then, you will not be able to see the eval performance on GPT-4. **Starting April 10, the minimum eval count is 15 samples, we hope this makes it easier to create and contribute evals.** Also, please note that we're using **Git LFS** for storing the JSON files, so please make sure that you move the JSON file to Git LFS before submitting a PR. Details on how to use Git LFS are available [here](https://git-lfs.com). ## Eval details 📑 ### Eval name 3D Globe Movement ### Eval description This eval tests an LLMs ability to understand 3D movement through space, in particular movement on or through planet Earth. Each example provides a starting point and a path consisting of one or two movements, and the expected answer is a state/province or ocean. Similar to the evals from #462 and #1060, this eval shows how difficult movement is for LLMs to understand, and builds upon those by showing how the problem is seemingly magnified by 3D movement and/or by requesting a region as answer rather than numerical positions. Testing on gpt-3.5-turbo, accuracy ranges from ~0.24 to ~0.31 ### What makes this a useful eval? This eval demonstrates that a long series of steps is not necessary in order to create a path that GPT is unable to follow, and that a simple trip to the planet's core and back again, with a slight offset in any direction, will often get it lost. Whereas it can often handle "travel 15 degrees East", hiding that actual travel behind a 2-step 3D path significantly hurts the model's performance. Interestingly, this eval seems to demonstrate the statistical rather than reasoning nature of GPT, as regardless of starting point or path, it shows a bias towards answering with oceans, especially the Pacific Ocean. ## Criteria for a good eval ✅ Below are some of the criteria we look for in a good eval. In general, we are seeking cases where the model does not do a good job despite being capable of generating a good response (note that there are some things large language models cannot do, so those would not make good evals). Your eval should be: - [x] Thematically consistent: The eval should be thematically consistent. We'd like to see a number of prompts all demonstrating some particular failure mode. For example, we can create an eval on cases where the model fails to reason about the physical world. - [x] Contains failures where a human can do the task, but either GPT-4 or GPT-3.5-Turbo could not. - [x] Includes good signal around what is the right behavior. This means either a correct answer for `Basic` evals or the `Fact` Model-graded eval, or an exhaustive rubric for evaluating answers for the `Criteria` Model-graded eval. - [x] **Include at least 15 high-quality examples.** If there is anything else that makes your eval worth including, please document it below. ### Unique eval value > Insert what makes your eval high quality that was not mentioned above. (Not required) ## Eval structure 🏗️ Your eval should - [x] Check that your data is in `evals/registry/data/{name}` - [x] Check that your YAML is registered at `evals/registry/evals/{name}.yaml` - [x] Ensure you have the right to use the data you submit via this eval (For now, we will only be approving evals that use one of the existing eval classes. You may still write custom eval classes for your own cases, and we may consider merging them in the future.) ## Final checklist 👀 ### Submission agreement By contributing to Evals, you are agreeing to make your evaluation logic and data under the same MIT license as this repository. You must have adequate rights to upload any data used in an Eval. OpenAI reserves the right to use this data in future service improvements to our product. Contributions to OpenAI Evals will be subject to our usual Usage Policies (<https://platform.openai.com/docs/usage-policies>). - [x] I agree that my submission will be made available under an MIT license and complies with OpenAI's usage policies. ### Email address validation If your submission is accepted, we will be granting GPT-4 access to a limited number of contributors. Access will be given to the email address associated with the merged pull request. - [x] I acknowledge that GPT-4 access will only be granted, if applicable, to the email address used for my merged pull request. ### Limited availability acknowledgment We know that you might be excited to contribute to OpenAI's mission, help improve our models, and gain access to GPT-4. However, due to the requirements mentioned above and the high volume of submissions, we will not be able to accept all submissions and thus not grant everyone who opens a PR GPT-4 access. We know this is disappointing, but we hope to set the right expectation before you open this PR. - [x] I understand that opening a PR, even if it meets the requirements above, does not guarantee the PR will be merged nor GPT-4 access be granted. ### Submit eval - [x] I have filled out all required fields of this form - [x] I have used **Git LFS** for the Eval JSON data - [x] (Ignore if not submitting code) I have run `pip install pre-commit; pre-commit install` and have verified that `black`, `isort`, and `autoflake` are running when I commit and push Failure to fill out all required fields will result in the PR being closed. ### Eval JSON data Since we are using Git LFS, we are asking eval submitters to add in as many Eval Samples (at least 5) from their contribution here: <details> <summary>View evals in JSON</summary> ### Eval ```jsonl {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 15 degree offset to the East"}], "ideal": "Colorado"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel due East 15 degrees"}], "ideal": "Colorado"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel due East 0.1 degrees"}], "ideal": "California"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel due East 1 meter"}], "ideal": "California"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel 0 meter"}], "ideal": "California"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and make one complete revolution around the planet"}], "ideal": "California"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 1 degree offset to the East"}], "ideal": "California"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 0.1 degree offset to the East"}], "ideal": "California"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 0.01 degree offset to the East"}], "ideal": "California"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 1 degree offset to the West"}], "ideal": "Pacific Ocean"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 90 degree offset to the East"}], "ideal": "Atlantic Ocean"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 180 degree offset to the East"}], "ideal": "Ahal"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 1 degree offset to the North"}], "ideal": "California"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of Kansas City and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 15 degree offset to the East"}], "ideal": "West Virginia"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of Kansas City and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 15 degree offset to the West"}], "ideal": "Utah"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 1 degree offset to the East"}], "ideal": "Atlantic Ocean"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel due East 10 degrees"}], "ideal": "Atlantic Ocean"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel due East 500 kilometers"}], "ideal": "Atlantic Ocean"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 1 degree offset to the West"}], "ideal": "New Jersey"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 10 degree offset to the West"}], "ideal": "Ohio"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel due West 10 degrees"}], "ideal": "Ohio"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel due West 15 degrees"}], "ideal": "Illinois"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel due West 25 degrees"}], "ideal": "Nebraska"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel due West 30 degrees"}], "ideal": "Colorado"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel due West 35 degrees"}], "ideal": "Colorado"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of Oklahoma City and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 0.1 degree offset to the East"}], "ideal": "Oklahoma"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of Oklahoma City and travel directly downwards to the center of the Earth, then straight up, back to the surface along the same path that was traveled downards."}], "ideal": "Oklahoma"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of Oklahoma City and travel directly downwards to the center of the Earth, then continue onwards to the other side of the planet"}], "ideal": "Xinjiang"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of Oklahoma City and travel directly downwards through to the other side of the Earth"}], "ideal": "Xinjiang"} ``` </details>
arbreton
pushed a commit
to arbreton/evals
that referenced
this pull request
Jul 8, 2023
# Thank you for contributing an eval!♥️ 🚨 Please make sure your PR follows these guidelines, __failure to follow the guidelines below will result in the PR being closed automatically__. Note that even if the criteria are met, that does not guarantee the PR will be merged nor GPT-4 access granted. 🚨 __PLEASE READ THIS__: In order for a PR to be merged, it must fail on GPT-4. We are aware that right now, users do not have access, so you will not be able to tell if the eval fails or not. Please run your eval with GPT-3.5-Turbo, but keep in mind as we run the eval, if GPT-4 gets higher than 90% on the eval, we will likely reject since GPT-4 is already capable of completing the task. We plan to roll out a way for users submitting evals to see the eval performance on GPT-4 soon. Stay tuned! Until then, you will not be able to see the eval performance on GPT-4. **Starting April 10, the minimum eval count is 15 samples, we hope this makes it easier to create and contribute evals.** Also, pelase note that we're using **Git LFS** for storing the JSON files, so please make sure that you move the JSON file to Git LFS before submitting a PR. Details on how to use Git LFS are available [here](https://git-lfs.com). ## Eval details 📑 ### Eval name Cardinal Directions ### Eval description This eval tests the model's ability to make an internal representation of relative positions and reason about cardinal directions. It's a refinement of my previously submitted PR Relative Orientations (openai#1000 ), containing a handful of selected problems which make a more thematically consistent set of samples. Adjustments were made to improve the clarity, quality, as well as the diversity of parameters in the selected prompts for a more comprehensive assessment of problem-solving ability. ### What makes this a useful eval? It helps test the model's spatial reasoning ability ## Criteria for a good eval ✅ Below are some of the criteria we look for in a good eval. In general, we are seeking cases where the model does not do a good job despite being capable of generating a good response (note that there are some things large language models cannot do, so those would not make good evals). Your eval should be: - [x] Thematically consistent: The eval should be thematically consistent. We'd like to see a number of prompts all demonstrating some particular failure mode. For example, we can create an eval on cases where the model fails to reason about the physical world. - [x] Contains failures where a human can do the task, but either GPT-4 or GPT-3.5-Turbo could not. - [x] Includes good signal around what is the right behavior. This means either a correct answer for `Basic` evals or the `Fact` Model-graded eval, or an exhaustive rubric for evaluating answers for the `Criteria` Model-graded eval. - [x] **Include at least 15 high quality examples.** If there is anything else that makes your eval worth including, please document it below. ### Unique eval value > Insert what makes your eval high quality that was not mentioned above. (Not required) ## Eval structure 🏗️ Your eval should - [x] Check that your data is in `evals/registry/data/{name}` - [x] Check that your yaml is registered at `evals/registry/evals/{name}.yaml` - [x] Ensure you have the right to use the data you submit via this eval (For now, we will only be approving evals that use one of the existing eval classes. You may still write custom eval classes for your own cases, and we may consider merging them in the future.) ## Final checklist 👀 ### Submission agreement By contributing to Evals, you are agreeing to make your evaluation logic and data under the same MIT license as this repository. You must have adequate rights to upload any data used in an Eval. OpenAI reserves the right to use this data in future service improvements to our product. Contributions to OpenAI Evals will be subject to our usual Usage Policies (https://platform.openai.com/docs/usage-policies). - [x] I agree that my submission will be made available under an MIT license and complies with OpenAI's usage policies. ### Email address validation If your submission is accepted, we will be granting GPT-4 access to a limited number of contributors. Access will be given to the email address associated with the merged pull request. - [x] I acknowledge that GPT-4 access will only be granted, if applicable, to the email address used for my merged pull request. ### Limited availability acknowledgement We know that you might be excited to contribute to OpenAI's mission, help improve our models, and gain access to GPT-4. However, due to the requirements mentioned above and high volume of submissions, we will not be able to accept all submissions and thus not grant everyone who opens a PR GPT-4 access. We know this is disappointing, but we hope to set the right expectation before you open this PR. - [x] I understand that opening a PR, even if it meets the requirements above, does not guarantee the PR will be merged nor GPT-4 access granted. ### Submit eval - [x] I have filled out all required fields of this form - [x] I have used **Git LFS** for the Eval JSON data - [ ] (Ignore if not submitting code) I have run `pip install pre-commit; pre-commit install` and have verified that `black`, `isort`, and `autoflake` are running when I commit and push Failure to fill out all required fields will result in the PR being closed. ### Eval JSON data Since we are using Git LFS, we are asking eval submitters to add in as many Eval Samples (at least 5) from their contribution here: <details> <summary>View evals in JSON</summary> ### Eval ```jsonl {"input": [{"role": "user", "content": "Chloe, Kate, Drew, and Mikey are gathered in a circle. Drew is opposite Chloe and Kate sees Chloe to her left. At the center is a bottle which points towards Mikey. When Chloe spins the bottle, it rotates two and three-quarters of a full circle. Who is the person opposite the direction the bottle is pointing? Please respond with only one of the following options: \"Chloe\", \"Mikey\", \"Drew\", \"Kate\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "Drew"} {"input": [{"role": "user", "content": "Daniel, Emily, Richard, and Max are gathered in a circle. Richard is opposite Daniel and Emily sees Daniel to her left. If Daniel points towards Max he points North West. If Emily points towards Richard what direction does she point? Please respond with only one of the following options: \"North\", \"South\", \"East\", \"West\", \"North East\", \"North West\", \"South East\", \"South West\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "North West"} {"input": [{"role": "user", "content": "Leonard, Marie, Carl, and Martin are gathered in a circle. Carl is opposite Leonard and Marie sees Leonard to her right. If Carl points towards Leonard, he points directly North. If Leonard points towards Martin, in what direction does he point? Please respond with only one of the following options: \"North\", \"South\", \"East\", \"West\", \"North East\", \"North West\", \"South East\", \"South West\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "South West"} {"input": [{"role": "user", "content": "Two perpendicular paths intersect at a cross. There is a banana peel along one path away from the intersection. Drew is walking directly North along one path when he sees the banana peel to his right. Frank sees Drew ahead of him as they both move towards the intersection. When Frank takes a turn at the intersection he avoids the banana peel by walking around it. In which direction did Frank turn at the intersection? Please respond with only one of the following options: \"North\", \"South\", \"East\", \"West\", \"North East\", \"North West\", \"South East\", \"South West\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "East"} {"input": [{"role": "user", "content": "Two perpendicular paths intersect in a cross. Alan walks along one path while Gordon walks along the other. Gordon is walking directly North. As they both move towards the intersection, Gordon sees Alan to his left. What direction is Gordon headed? Please respond with only one of the following options: \"North\", \"South\", \"West\", \"East\", \"North West\", \"North East\", \"South West\", \"South East\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "West"} {"input": [{"role": "user", "content": "Two birds are flying in perpendicular paths. One bird is flying Northward and the other Eastward. As Will is walking a straight path, he sees both birds on his right moving away from each other. Which direction is Will headed? Please respond with only one of the following options: \"North\", \"South\", \"East\", \"West\", \"North East\", \"North West\", \"South East\", \"South West\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "North West"} {"input": [{"role": "user", "content": "Two birds are flying in perpendicular paths. One bird is flying Southward and the other Westward. As Ryan is walking a straight path, he sees both birds on his left moving away from each other. Which direction is Ryan headed? Please respond with only one of the following options: \"North\", \"South\", \"East\", \"West\", \"North East\", \"North West\", \"South East\", \"South West\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "North West"} {"input": [{"role": "user", "content": "I face a circular fountain in such a way that a statue of Alan Turing at the center of the fountain faces me. I walk straight towards the fountain until I reach its edge. I then start walking counter-clockwise along the edge of the fountain. After walking three-quarters of a circle around the fountain I start walking a straight path. If Alan is facing North, which direction am I headed? Please respond only with \"North\", \"South\", \"West\", or \"East\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "North"} {"input": [{"role": "user", "content": "I face a circular fountain in such a way that a statue of Alan Turing at the center of the fountain faces me. I walk straight towards the fountain until I reach its edge. I then start walking counter-clockwise along the edge of the fountain. After walking full circle around the fountain I start walking a straight path. If Alan is facing East, which direction am I headed? Please respond only with \"North\", \"South\", \"West\", or \"East\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "North"} {"input": [{"role": "user", "content": "I face a circular fountain in such a way that a statue of Alan Turing at the center of the fountain faces me. I walk straight towards the fountain until I reach its edge. I then start walking clockwise along the edge of the fountain. After walking quarter circle around the fountain I start walking a straight path. If Alan is facing South, which direction am I headed? Please respond only with \"North\", \"South\", \"East\", or \"West\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "North"} {"input": [{"role": "user", "content": "I face a circular fountain in such a way that a statue of Alan Turing at the center of the fountain faces me. I walk straight towards the fountain until I reach its edge. I then start walking clockwise along the edge of the fountain. After walking half circle around the fountain I start walking a straight path. If Alan is facing West, which direction am I headed? Please respond only with \"North\", \"South\", \"East\", or \"West\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "South"} {"input": [{"role": "user", "content": "I am walking a straight path in a courtyard as the sun is setting. I see a bird fly towards the sun. The bird came from my right and our paths are perpendicular. Which direction am I headed? Please respond only with \"South\". \"East\", \"North\" or \"West\"."}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "North"} {"input": [{"role": "user", "content": "I am walking a straight path in a courtyard as the sun is setting. I see a bird fly away from the sun. The bird came from my left and our paths are perpendicular. Which direction am I headed? Please respond only with \"South\". \"East\", \"North\" or \"West\"."}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "North"} {"input": [{"role": "user", "content": "I am walking a straight path in a courtyard as the sun is setting. I see a bird fly away from the sun. The bird came from my right and our paths are perpendicular. Which direction am I headed? Please respond only with \"South\". \"East\", \"North\" or \"West\"."}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "South"} {"input": [{"role": "user", "content": "I am walking a straight path in a courtyard as the sun is setting. I see a bird fly towards the sun. The bird came from my left and our paths are perpendicular. Which direction am I headed? Please respond only with \"South\". \"East\", \"North\" or \"West\"."}, {"role":"system", "content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "South"} ``` </details>
arbreton
pushed a commit
to arbreton/evals
that referenced
this pull request
Jul 8, 2023
# Thank you for contributing an eval!♥️ 🚨 Please make sure your PR follows these guidelines, **failure to follow the guidelines below will result in the PR being closed automatically**. Note that even if the criteria are met, that does not guarantee the PR will be merged nor GPT-4 access be granted. 🚨 **PLEASE READ THIS**: In order for a PR to be merged, it must fail on GPT-4. We are aware that right now, users do not have access, so you will not be able to tell if the eval fails or not. Please run your eval with GPT-3.5-Turbo, but keep in mind as we run the eval, if GPT-4 gets higher than 90% on the eval, we will likely reject it since GPT-4 is already capable of completing the task. We plan to roll out a way for users submitting evals to see the eval performance on GPT-4 soon. Stay tuned! Until then, you will not be able to see the eval performance on GPT-4. **Starting April 10, the minimum eval count is 15 samples, we hope this makes it easier to create and contribute evals.** Also, please note that we're using **Git LFS** for storing the JSON files, so please make sure that you move the JSON file to Git LFS before submitting a PR. Details on how to use Git LFS are available [here](https://git-lfs.com). ## Eval details 📑 ### Eval name 3D Globe Movement ### Eval description This eval tests an LLMs ability to understand 3D movement through space, in particular movement on or through planet Earth. Each example provides a starting point and a path consisting of one or two movements, and the expected answer is a state/province or ocean. Similar to the evals from openai#462 and openai#1060, this eval shows how difficult movement is for LLMs to understand, and builds upon those by showing how the problem is seemingly magnified by 3D movement and/or by requesting a region as answer rather than numerical positions. Testing on gpt-3.5-turbo, accuracy ranges from ~0.24 to ~0.31 ### What makes this a useful eval? This eval demonstrates that a long series of steps is not necessary in order to create a path that GPT is unable to follow, and that a simple trip to the planet's core and back again, with a slight offset in any direction, will often get it lost. Whereas it can often handle "travel 15 degrees East", hiding that actual travel behind a 2-step 3D path significantly hurts the model's performance. Interestingly, this eval seems to demonstrate the statistical rather than reasoning nature of GPT, as regardless of starting point or path, it shows a bias towards answering with oceans, especially the Pacific Ocean. ## Criteria for a good eval ✅ Below are some of the criteria we look for in a good eval. In general, we are seeking cases where the model does not do a good job despite being capable of generating a good response (note that there are some things large language models cannot do, so those would not make good evals). Your eval should be: - [x] Thematically consistent: The eval should be thematically consistent. We'd like to see a number of prompts all demonstrating some particular failure mode. For example, we can create an eval on cases where the model fails to reason about the physical world. - [x] Contains failures where a human can do the task, but either GPT-4 or GPT-3.5-Turbo could not. - [x] Includes good signal around what is the right behavior. This means either a correct answer for `Basic` evals or the `Fact` Model-graded eval, or an exhaustive rubric for evaluating answers for the `Criteria` Model-graded eval. - [x] **Include at least 15 high-quality examples.** If there is anything else that makes your eval worth including, please document it below. ### Unique eval value > Insert what makes your eval high quality that was not mentioned above. (Not required) ## Eval structure 🏗️ Your eval should - [x] Check that your data is in `evals/registry/data/{name}` - [x] Check that your YAML is registered at `evals/registry/evals/{name}.yaml` - [x] Ensure you have the right to use the data you submit via this eval (For now, we will only be approving evals that use one of the existing eval classes. You may still write custom eval classes for your own cases, and we may consider merging them in the future.) ## Final checklist 👀 ### Submission agreement By contributing to Evals, you are agreeing to make your evaluation logic and data under the same MIT license as this repository. You must have adequate rights to upload any data used in an Eval. OpenAI reserves the right to use this data in future service improvements to our product. Contributions to OpenAI Evals will be subject to our usual Usage Policies (<https://platform.openai.com/docs/usage-policies>). - [x] I agree that my submission will be made available under an MIT license and complies with OpenAI's usage policies. ### Email address validation If your submission is accepted, we will be granting GPT-4 access to a limited number of contributors. Access will be given to the email address associated with the merged pull request. - [x] I acknowledge that GPT-4 access will only be granted, if applicable, to the email address used for my merged pull request. ### Limited availability acknowledgment We know that you might be excited to contribute to OpenAI's mission, help improve our models, and gain access to GPT-4. However, due to the requirements mentioned above and the high volume of submissions, we will not be able to accept all submissions and thus not grant everyone who opens a PR GPT-4 access. We know this is disappointing, but we hope to set the right expectation before you open this PR. - [x] I understand that opening a PR, even if it meets the requirements above, does not guarantee the PR will be merged nor GPT-4 access be granted. ### Submit eval - [x] I have filled out all required fields of this form - [x] I have used **Git LFS** for the Eval JSON data - [x] (Ignore if not submitting code) I have run `pip install pre-commit; pre-commit install` and have verified that `black`, `isort`, and `autoflake` are running when I commit and push Failure to fill out all required fields will result in the PR being closed. ### Eval JSON data Since we are using Git LFS, we are asking eval submitters to add in as many Eval Samples (at least 5) from their contribution here: <details> <summary>View evals in JSON</summary> ### Eval ```jsonl {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 15 degree offset to the East"}], "ideal": "Colorado"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel due East 15 degrees"}], "ideal": "Colorado"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel due East 0.1 degrees"}], "ideal": "California"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel due East 1 meter"}], "ideal": "California"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel 0 meter"}], "ideal": "California"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and make one complete revolution around the planet"}], "ideal": "California"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 1 degree offset to the East"}], "ideal": "California"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 0.1 degree offset to the East"}], "ideal": "California"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 0.01 degree offset to the East"}], "ideal": "California"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 1 degree offset to the West"}], "ideal": "Pacific Ocean"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 90 degree offset to the East"}], "ideal": "Atlantic Ocean"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 180 degree offset to the East"}], "ideal": "Ahal"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 1 degree offset to the North"}], "ideal": "California"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of Kansas City and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 15 degree offset to the East"}], "ideal": "West Virginia"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of Kansas City and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 15 degree offset to the West"}], "ideal": "Utah"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 1 degree offset to the East"}], "ideal": "Atlantic Ocean"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel due East 10 degrees"}], "ideal": "Atlantic Ocean"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel due East 500 kilometers"}], "ideal": "Atlantic Ocean"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 1 degree offset to the West"}], "ideal": "New Jersey"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 10 degree offset to the West"}], "ideal": "Ohio"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel due West 10 degrees"}], "ideal": "Ohio"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel due West 15 degrees"}], "ideal": "Illinois"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel due West 25 degrees"}], "ideal": "Nebraska"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel due West 30 degrees"}], "ideal": "Colorado"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel due West 35 degrees"}], "ideal": "Colorado"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of Oklahoma City and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 0.1 degree offset to the East"}], "ideal": "Oklahoma"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of Oklahoma City and travel directly downwards to the center of the Earth, then straight up, back to the surface along the same path that was traveled downards."}], "ideal": "Oklahoma"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of Oklahoma City and travel directly downwards to the center of the Earth, then continue onwards to the other side of the planet"}], "ideal": "Xinjiang"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of Oklahoma City and travel directly downwards through to the other side of the Earth"}], "ideal": "Xinjiang"} ``` </details>
jacobbieker
pushed a commit
to withmartian/-ARCHIVED--router-evals
that referenced
this pull request
Jan 9, 2024
# Thank you for contributing an eval!♥️ 🚨 Please make sure your PR follows these guidelines, __failure to follow the guidelines below will result in the PR being closed automatically__. Note that even if the criteria are met, that does not guarantee the PR will be merged nor GPT-4 access granted. 🚨 __PLEASE READ THIS__: In order for a PR to be merged, it must fail on GPT-4. We are aware that right now, users do not have access, so you will not be able to tell if the eval fails or not. Please run your eval with GPT-3.5-Turbo, but keep in mind as we run the eval, if GPT-4 gets higher than 90% on the eval, we will likely reject since GPT-4 is already capable of completing the task. We plan to roll out a way for users submitting evals to see the eval performance on GPT-4 soon. Stay tuned! Until then, you will not be able to see the eval performance on GPT-4. **Starting April 10, the minimum eval count is 15 samples, we hope this makes it easier to create and contribute evals.** Also, pelase note that we're using **Git LFS** for storing the JSON files, so please make sure that you move the JSON file to Git LFS before submitting a PR. Details on how to use Git LFS are available [here](https://git-lfs.com). ## Eval details 📑 ### Eval name Cardinal Directions ### Eval description This eval tests the model's ability to make an internal representation of relative positions and reason about cardinal directions. It's a refinement of my previously submitted PR Relative Orientations (openai#1000 ), containing a handful of selected problems which make a more thematically consistent set of samples. Adjustments were made to improve the clarity, quality, as well as the diversity of parameters in the selected prompts for a more comprehensive assessment of problem-solving ability. ### What makes this a useful eval? It helps test the model's spatial reasoning ability ## Criteria for a good eval ✅ Below are some of the criteria we look for in a good eval. In general, we are seeking cases where the model does not do a good job despite being capable of generating a good response (note that there are some things large language models cannot do, so those would not make good evals). Your eval should be: - [x] Thematically consistent: The eval should be thematically consistent. We'd like to see a number of prompts all demonstrating some particular failure mode. For example, we can create an eval on cases where the model fails to reason about the physical world. - [x] Contains failures where a human can do the task, but either GPT-4 or GPT-3.5-Turbo could not. - [x] Includes good signal around what is the right behavior. This means either a correct answer for `Basic` evals or the `Fact` Model-graded eval, or an exhaustive rubric for evaluating answers for the `Criteria` Model-graded eval. - [x] **Include at least 15 high quality examples.** If there is anything else that makes your eval worth including, please document it below. ### Unique eval value > Insert what makes your eval high quality that was not mentioned above. (Not required) ## Eval structure 🏗️ Your eval should - [x] Check that your data is in `evals/registry/data/{name}` - [x] Check that your yaml is registered at `evals/registry/evals/{name}.yaml` - [x] Ensure you have the right to use the data you submit via this eval (For now, we will only be approving evals that use one of the existing eval classes. You may still write custom eval classes for your own cases, and we may consider merging them in the future.) ## Final checklist 👀 ### Submission agreement By contributing to Evals, you are agreeing to make your evaluation logic and data under the same MIT license as this repository. You must have adequate rights to upload any data used in an Eval. OpenAI reserves the right to use this data in future service improvements to our product. Contributions to OpenAI Evals will be subject to our usual Usage Policies (https://platform.openai.com/docs/usage-policies). - [x] I agree that my submission will be made available under an MIT license and complies with OpenAI's usage policies. ### Email address validation If your submission is accepted, we will be granting GPT-4 access to a limited number of contributors. Access will be given to the email address associated with the merged pull request. - [x] I acknowledge that GPT-4 access will only be granted, if applicable, to the email address used for my merged pull request. ### Limited availability acknowledgement We know that you might be excited to contribute to OpenAI's mission, help improve our models, and gain access to GPT-4. However, due to the requirements mentioned above and high volume of submissions, we will not be able to accept all submissions and thus not grant everyone who opens a PR GPT-4 access. We know this is disappointing, but we hope to set the right expectation before you open this PR. - [x] I understand that opening a PR, even if it meets the requirements above, does not guarantee the PR will be merged nor GPT-4 access granted. ### Submit eval - [x] I have filled out all required fields of this form - [x] I have used **Git LFS** for the Eval JSON data - [ ] (Ignore if not submitting code) I have run `pip install pre-commit; pre-commit install` and have verified that `black`, `isort`, and `autoflake` are running when I commit and push Failure to fill out all required fields will result in the PR being closed. ### Eval JSON data Since we are using Git LFS, we are asking eval submitters to add in as many Eval Samples (at least 5) from their contribution here: <details> <summary>View evals in JSON</summary> ### Eval ```jsonl {"input": [{"role": "user", "content": "Chloe, Kate, Drew, and Mikey are gathered in a circle. Drew is opposite Chloe and Kate sees Chloe to her left. At the center is a bottle which points towards Mikey. When Chloe spins the bottle, it rotates two and three-quarters of a full circle. Who is the person opposite the direction the bottle is pointing? Please respond with only one of the following options: \"Chloe\", \"Mikey\", \"Drew\", \"Kate\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "Drew"} {"input": [{"role": "user", "content": "Daniel, Emily, Richard, and Max are gathered in a circle. Richard is opposite Daniel and Emily sees Daniel to her left. If Daniel points towards Max he points North West. If Emily points towards Richard what direction does she point? Please respond with only one of the following options: \"North\", \"South\", \"East\", \"West\", \"North East\", \"North West\", \"South East\", \"South West\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "North West"} {"input": [{"role": "user", "content": "Leonard, Marie, Carl, and Martin are gathered in a circle. Carl is opposite Leonard and Marie sees Leonard to her right. If Carl points towards Leonard, he points directly North. If Leonard points towards Martin, in what direction does he point? Please respond with only one of the following options: \"North\", \"South\", \"East\", \"West\", \"North East\", \"North West\", \"South East\", \"South West\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "South West"} {"input": [{"role": "user", "content": "Two perpendicular paths intersect at a cross. There is a banana peel along one path away from the intersection. Drew is walking directly North along one path when he sees the banana peel to his right. Frank sees Drew ahead of him as they both move towards the intersection. When Frank takes a turn at the intersection he avoids the banana peel by walking around it. In which direction did Frank turn at the intersection? Please respond with only one of the following options: \"North\", \"South\", \"East\", \"West\", \"North East\", \"North West\", \"South East\", \"South West\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "East"} {"input": [{"role": "user", "content": "Two perpendicular paths intersect in a cross. Alan walks along one path while Gordon walks along the other. Gordon is walking directly North. As they both move towards the intersection, Gordon sees Alan to his left. What direction is Gordon headed? Please respond with only one of the following options: \"North\", \"South\", \"West\", \"East\", \"North West\", \"North East\", \"South West\", \"South East\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "West"} {"input": [{"role": "user", "content": "Two birds are flying in perpendicular paths. One bird is flying Northward and the other Eastward. As Will is walking a straight path, he sees both birds on his right moving away from each other. Which direction is Will headed? Please respond with only one of the following options: \"North\", \"South\", \"East\", \"West\", \"North East\", \"North West\", \"South East\", \"South West\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "North West"} {"input": [{"role": "user", "content": "Two birds are flying in perpendicular paths. One bird is flying Southward and the other Westward. As Ryan is walking a straight path, he sees both birds on his left moving away from each other. Which direction is Ryan headed? Please respond with only one of the following options: \"North\", \"South\", \"East\", \"West\", \"North East\", \"North West\", \"South East\", \"South West\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "North West"} {"input": [{"role": "user", "content": "I face a circular fountain in such a way that a statue of Alan Turing at the center of the fountain faces me. I walk straight towards the fountain until I reach its edge. I then start walking counter-clockwise along the edge of the fountain. After walking three-quarters of a circle around the fountain I start walking a straight path. If Alan is facing North, which direction am I headed? Please respond only with \"North\", \"South\", \"West\", or \"East\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "North"} {"input": [{"role": "user", "content": "I face a circular fountain in such a way that a statue of Alan Turing at the center of the fountain faces me. I walk straight towards the fountain until I reach its edge. I then start walking counter-clockwise along the edge of the fountain. After walking full circle around the fountain I start walking a straight path. If Alan is facing East, which direction am I headed? Please respond only with \"North\", \"South\", \"West\", or \"East\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "North"} {"input": [{"role": "user", "content": "I face a circular fountain in such a way that a statue of Alan Turing at the center of the fountain faces me. I walk straight towards the fountain until I reach its edge. I then start walking clockwise along the edge of the fountain. After walking quarter circle around the fountain I start walking a straight path. If Alan is facing South, which direction am I headed? Please respond only with \"North\", \"South\", \"East\", or \"West\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "North"} {"input": [{"role": "user", "content": "I face a circular fountain in such a way that a statue of Alan Turing at the center of the fountain faces me. I walk straight towards the fountain until I reach its edge. I then start walking clockwise along the edge of the fountain. After walking half circle around the fountain I start walking a straight path. If Alan is facing West, which direction am I headed? Please respond only with \"North\", \"South\", \"East\", or \"West\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "South"} {"input": [{"role": "user", "content": "I am walking a straight path in a courtyard as the sun is setting. I see a bird fly towards the sun. The bird came from my right and our paths are perpendicular. Which direction am I headed? Please respond only with \"South\". \"East\", \"North\" or \"West\"."}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "North"} {"input": [{"role": "user", "content": "I am walking a straight path in a courtyard as the sun is setting. I see a bird fly away from the sun. The bird came from my left and our paths are perpendicular. Which direction am I headed? Please respond only with \"South\". \"East\", \"North\" or \"West\"."}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "North"} {"input": [{"role": "user", "content": "I am walking a straight path in a courtyard as the sun is setting. I see a bird fly away from the sun. The bird came from my right and our paths are perpendicular. Which direction am I headed? Please respond only with \"South\". \"East\", \"North\" or \"West\"."}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "South"} {"input": [{"role": "user", "content": "I am walking a straight path in a courtyard as the sun is setting. I see a bird fly towards the sun. The bird came from my left and our paths are perpendicular. Which direction am I headed? Please respond only with \"South\". \"East\", \"North\" or \"West\"."}, {"role":"system", "content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "South"} ``` </details>
jacobbieker
pushed a commit
to withmartian/-ARCHIVED--router-evals
that referenced
this pull request
Jan 9, 2024
# Thank you for contributing an eval!♥️ 🚨 Please make sure your PR follows these guidelines, **failure to follow the guidelines below will result in the PR being closed automatically**. Note that even if the criteria are met, that does not guarantee the PR will be merged nor GPT-4 access be granted. 🚨 **PLEASE READ THIS**: In order for a PR to be merged, it must fail on GPT-4. We are aware that right now, users do not have access, so you will not be able to tell if the eval fails or not. Please run your eval with GPT-3.5-Turbo, but keep in mind as we run the eval, if GPT-4 gets higher than 90% on the eval, we will likely reject it since GPT-4 is already capable of completing the task. We plan to roll out a way for users submitting evals to see the eval performance on GPT-4 soon. Stay tuned! Until then, you will not be able to see the eval performance on GPT-4. **Starting April 10, the minimum eval count is 15 samples, we hope this makes it easier to create and contribute evals.** Also, please note that we're using **Git LFS** for storing the JSON files, so please make sure that you move the JSON file to Git LFS before submitting a PR. Details on how to use Git LFS are available [here](https://git-lfs.com). ## Eval details 📑 ### Eval name 3D Globe Movement ### Eval description This eval tests an LLMs ability to understand 3D movement through space, in particular movement on or through planet Earth. Each example provides a starting point and a path consisting of one or two movements, and the expected answer is a state/province or ocean. Similar to the evals from openai#462 and openai#1060, this eval shows how difficult movement is for LLMs to understand, and builds upon those by showing how the problem is seemingly magnified by 3D movement and/or by requesting a region as answer rather than numerical positions. Testing on gpt-3.5-turbo, accuracy ranges from ~0.24 to ~0.31 ### What makes this a useful eval? This eval demonstrates that a long series of steps is not necessary in order to create a path that GPT is unable to follow, and that a simple trip to the planet's core and back again, with a slight offset in any direction, will often get it lost. Whereas it can often handle "travel 15 degrees East", hiding that actual travel behind a 2-step 3D path significantly hurts the model's performance. Interestingly, this eval seems to demonstrate the statistical rather than reasoning nature of GPT, as regardless of starting point or path, it shows a bias towards answering with oceans, especially the Pacific Ocean. ## Criteria for a good eval ✅ Below are some of the criteria we look for in a good eval. In general, we are seeking cases where the model does not do a good job despite being capable of generating a good response (note that there are some things large language models cannot do, so those would not make good evals). Your eval should be: - [x] Thematically consistent: The eval should be thematically consistent. We'd like to see a number of prompts all demonstrating some particular failure mode. For example, we can create an eval on cases where the model fails to reason about the physical world. - [x] Contains failures where a human can do the task, but either GPT-4 or GPT-3.5-Turbo could not. - [x] Includes good signal around what is the right behavior. This means either a correct answer for `Basic` evals or the `Fact` Model-graded eval, or an exhaustive rubric for evaluating answers for the `Criteria` Model-graded eval. - [x] **Include at least 15 high-quality examples.** If there is anything else that makes your eval worth including, please document it below. ### Unique eval value > Insert what makes your eval high quality that was not mentioned above. (Not required) ## Eval structure 🏗️ Your eval should - [x] Check that your data is in `evals/registry/data/{name}` - [x] Check that your YAML is registered at `evals/registry/evals/{name}.yaml` - [x] Ensure you have the right to use the data you submit via this eval (For now, we will only be approving evals that use one of the existing eval classes. You may still write custom eval classes for your own cases, and we may consider merging them in the future.) ## Final checklist 👀 ### Submission agreement By contributing to Evals, you are agreeing to make your evaluation logic and data under the same MIT license as this repository. You must have adequate rights to upload any data used in an Eval. OpenAI reserves the right to use this data in future service improvements to our product. Contributions to OpenAI Evals will be subject to our usual Usage Policies (<https://platform.openai.com/docs/usage-policies>). - [x] I agree that my submission will be made available under an MIT license and complies with OpenAI's usage policies. ### Email address validation If your submission is accepted, we will be granting GPT-4 access to a limited number of contributors. Access will be given to the email address associated with the merged pull request. - [x] I acknowledge that GPT-4 access will only be granted, if applicable, to the email address used for my merged pull request. ### Limited availability acknowledgment We know that you might be excited to contribute to OpenAI's mission, help improve our models, and gain access to GPT-4. However, due to the requirements mentioned above and the high volume of submissions, we will not be able to accept all submissions and thus not grant everyone who opens a PR GPT-4 access. We know this is disappointing, but we hope to set the right expectation before you open this PR. - [x] I understand that opening a PR, even if it meets the requirements above, does not guarantee the PR will be merged nor GPT-4 access be granted. ### Submit eval - [x] I have filled out all required fields of this form - [x] I have used **Git LFS** for the Eval JSON data - [x] (Ignore if not submitting code) I have run `pip install pre-commit; pre-commit install` and have verified that `black`, `isort`, and `autoflake` are running when I commit and push Failure to fill out all required fields will result in the PR being closed. ### Eval JSON data Since we are using Git LFS, we are asking eval submitters to add in as many Eval Samples (at least 5) from their contribution here: <details> <summary>View evals in JSON</summary> ### Eval ```jsonl {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 15 degree offset to the East"}], "ideal": "Colorado"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel due East 15 degrees"}], "ideal": "Colorado"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel due East 0.1 degrees"}], "ideal": "California"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel due East 1 meter"}], "ideal": "California"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel 0 meter"}], "ideal": "California"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and make one complete revolution around the planet"}], "ideal": "California"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 1 degree offset to the East"}], "ideal": "California"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 0.1 degree offset to the East"}], "ideal": "California"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 0.01 degree offset to the East"}], "ideal": "California"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 1 degree offset to the West"}], "ideal": "Pacific Ocean"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 90 degree offset to the East"}], "ideal": "Atlantic Ocean"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 180 degree offset to the East"}], "ideal": "Ahal"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 1 degree offset to the North"}], "ideal": "California"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of Kansas City and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 15 degree offset to the East"}], "ideal": "West Virginia"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of Kansas City and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 15 degree offset to the West"}], "ideal": "Utah"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 1 degree offset to the East"}], "ideal": "Atlantic Ocean"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel due East 10 degrees"}], "ideal": "Atlantic Ocean"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel due East 500 kilometers"}], "ideal": "Atlantic Ocean"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 1 degree offset to the West"}], "ideal": "New Jersey"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 10 degree offset to the West"}], "ideal": "Ohio"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel due West 10 degrees"}], "ideal": "Ohio"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel due West 15 degrees"}], "ideal": "Illinois"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel due West 25 degrees"}], "ideal": "Nebraska"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel due West 30 degrees"}], "ideal": "Colorado"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel due West 35 degrees"}], "ideal": "Colorado"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of Oklahoma City and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 0.1 degree offset to the East"}], "ideal": "Oklahoma"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of Oklahoma City and travel directly downwards to the center of the Earth, then straight up, back to the surface along the same path that was traveled downards."}], "ideal": "Oklahoma"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of Oklahoma City and travel directly downwards to the center of the Earth, then continue onwards to the other side of the planet"}], "ideal": "Xinjiang"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of Oklahoma City and travel directly downwards through to the other side of the Earth"}], "ideal": "Xinjiang"} ``` </details>
Linmj-Judy
pushed a commit
to TablewareBox/evals
that referenced
this pull request
Feb 27, 2024
# Thank you for contributing an eval!♥️ 🚨 Please make sure your PR follows these guidelines, __failure to follow the guidelines below will result in the PR being closed automatically__. Note that even if the criteria are met, that does not guarantee the PR will be merged nor GPT-4 access granted. 🚨 __PLEASE READ THIS__: In order for a PR to be merged, it must fail on GPT-4. We are aware that right now, users do not have access, so you will not be able to tell if the eval fails or not. Please run your eval with GPT-3.5-Turbo, but keep in mind as we run the eval, if GPT-4 gets higher than 90% on the eval, we will likely reject since GPT-4 is already capable of completing the task. We plan to roll out a way for users submitting evals to see the eval performance on GPT-4 soon. Stay tuned! Until then, you will not be able to see the eval performance on GPT-4. **Starting April 10, the minimum eval count is 15 samples, we hope this makes it easier to create and contribute evals.** Also, pelase note that we're using **Git LFS** for storing the JSON files, so please make sure that you move the JSON file to Git LFS before submitting a PR. Details on how to use Git LFS are available [here](https://git-lfs.com). ## Eval details 📑 ### Eval name Cardinal Directions ### Eval description This eval tests the model's ability to make an internal representation of relative positions and reason about cardinal directions. It's a refinement of my previously submitted PR Relative Orientations (openai#1000 ), containing a handful of selected problems which make a more thematically consistent set of samples. Adjustments were made to improve the clarity, quality, as well as the diversity of parameters in the selected prompts for a more comprehensive assessment of problem-solving ability. ### What makes this a useful eval? It helps test the model's spatial reasoning ability ## Criteria for a good eval ✅ Below are some of the criteria we look for in a good eval. In general, we are seeking cases where the model does not do a good job despite being capable of generating a good response (note that there are some things large language models cannot do, so those would not make good evals). Your eval should be: - [x] Thematically consistent: The eval should be thematically consistent. We'd like to see a number of prompts all demonstrating some particular failure mode. For example, we can create an eval on cases where the model fails to reason about the physical world. - [x] Contains failures where a human can do the task, but either GPT-4 or GPT-3.5-Turbo could not. - [x] Includes good signal around what is the right behavior. This means either a correct answer for `Basic` evals or the `Fact` Model-graded eval, or an exhaustive rubric for evaluating answers for the `Criteria` Model-graded eval. - [x] **Include at least 15 high quality examples.** If there is anything else that makes your eval worth including, please document it below. ### Unique eval value > Insert what makes your eval high quality that was not mentioned above. (Not required) ## Eval structure 🏗️ Your eval should - [x] Check that your data is in `evals/registry/data/{name}` - [x] Check that your yaml is registered at `evals/registry/evals/{name}.yaml` - [x] Ensure you have the right to use the data you submit via this eval (For now, we will only be approving evals that use one of the existing eval classes. You may still write custom eval classes for your own cases, and we may consider merging them in the future.) ## Final checklist 👀 ### Submission agreement By contributing to Evals, you are agreeing to make your evaluation logic and data under the same MIT license as this repository. You must have adequate rights to upload any data used in an Eval. OpenAI reserves the right to use this data in future service improvements to our product. Contributions to OpenAI Evals will be subject to our usual Usage Policies (https://platform.openai.com/docs/usage-policies). - [x] I agree that my submission will be made available under an MIT license and complies with OpenAI's usage policies. ### Email address validation If your submission is accepted, we will be granting GPT-4 access to a limited number of contributors. Access will be given to the email address associated with the merged pull request. - [x] I acknowledge that GPT-4 access will only be granted, if applicable, to the email address used for my merged pull request. ### Limited availability acknowledgement We know that you might be excited to contribute to OpenAI's mission, help improve our models, and gain access to GPT-4. However, due to the requirements mentioned above and high volume of submissions, we will not be able to accept all submissions and thus not grant everyone who opens a PR GPT-4 access. We know this is disappointing, but we hope to set the right expectation before you open this PR. - [x] I understand that opening a PR, even if it meets the requirements above, does not guarantee the PR will be merged nor GPT-4 access granted. ### Submit eval - [x] I have filled out all required fields of this form - [x] I have used **Git LFS** for the Eval JSON data - [ ] (Ignore if not submitting code) I have run `pip install pre-commit; pre-commit install` and have verified that `black`, `isort`, and `autoflake` are running when I commit and push Failure to fill out all required fields will result in the PR being closed. ### Eval JSON data Since we are using Git LFS, we are asking eval submitters to add in as many Eval Samples (at least 5) from their contribution here: <details> <summary>View evals in JSON</summary> ### Eval ```jsonl {"input": [{"role": "user", "content": "Chloe, Kate, Drew, and Mikey are gathered in a circle. Drew is opposite Chloe and Kate sees Chloe to her left. At the center is a bottle which points towards Mikey. When Chloe spins the bottle, it rotates two and three-quarters of a full circle. Who is the person opposite the direction the bottle is pointing? Please respond with only one of the following options: \"Chloe\", \"Mikey\", \"Drew\", \"Kate\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "Drew"} {"input": [{"role": "user", "content": "Daniel, Emily, Richard, and Max are gathered in a circle. Richard is opposite Daniel and Emily sees Daniel to her left. If Daniel points towards Max he points North West. If Emily points towards Richard what direction does she point? Please respond with only one of the following options: \"North\", \"South\", \"East\", \"West\", \"North East\", \"North West\", \"South East\", \"South West\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "North West"} {"input": [{"role": "user", "content": "Leonard, Marie, Carl, and Martin are gathered in a circle. Carl is opposite Leonard and Marie sees Leonard to her right. If Carl points towards Leonard, he points directly North. If Leonard points towards Martin, in what direction does he point? Please respond with only one of the following options: \"North\", \"South\", \"East\", \"West\", \"North East\", \"North West\", \"South East\", \"South West\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "South West"} {"input": [{"role": "user", "content": "Two perpendicular paths intersect at a cross. There is a banana peel along one path away from the intersection. Drew is walking directly North along one path when he sees the banana peel to his right. Frank sees Drew ahead of him as they both move towards the intersection. When Frank takes a turn at the intersection he avoids the banana peel by walking around it. In which direction did Frank turn at the intersection? Please respond with only one of the following options: \"North\", \"South\", \"East\", \"West\", \"North East\", \"North West\", \"South East\", \"South West\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "East"} {"input": [{"role": "user", "content": "Two perpendicular paths intersect in a cross. Alan walks along one path while Gordon walks along the other. Gordon is walking directly North. As they both move towards the intersection, Gordon sees Alan to his left. What direction is Gordon headed? Please respond with only one of the following options: \"North\", \"South\", \"West\", \"East\", \"North West\", \"North East\", \"South West\", \"South East\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "West"} {"input": [{"role": "user", "content": "Two birds are flying in perpendicular paths. One bird is flying Northward and the other Eastward. As Will is walking a straight path, he sees both birds on his right moving away from each other. Which direction is Will headed? Please respond with only one of the following options: \"North\", \"South\", \"East\", \"West\", \"North East\", \"North West\", \"South East\", \"South West\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "North West"} {"input": [{"role": "user", "content": "Two birds are flying in perpendicular paths. One bird is flying Southward and the other Westward. As Ryan is walking a straight path, he sees both birds on his left moving away from each other. Which direction is Ryan headed? Please respond with only one of the following options: \"North\", \"South\", \"East\", \"West\", \"North East\", \"North West\", \"South East\", \"South West\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "North West"} {"input": [{"role": "user", "content": "I face a circular fountain in such a way that a statue of Alan Turing at the center of the fountain faces me. I walk straight towards the fountain until I reach its edge. I then start walking counter-clockwise along the edge of the fountain. After walking three-quarters of a circle around the fountain I start walking a straight path. If Alan is facing North, which direction am I headed? Please respond only with \"North\", \"South\", \"West\", or \"East\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "North"} {"input": [{"role": "user", "content": "I face a circular fountain in such a way that a statue of Alan Turing at the center of the fountain faces me. I walk straight towards the fountain until I reach its edge. I then start walking counter-clockwise along the edge of the fountain. After walking full circle around the fountain I start walking a straight path. If Alan is facing East, which direction am I headed? Please respond only with \"North\", \"South\", \"West\", or \"East\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "North"} {"input": [{"role": "user", "content": "I face a circular fountain in such a way that a statue of Alan Turing at the center of the fountain faces me. I walk straight towards the fountain until I reach its edge. I then start walking clockwise along the edge of the fountain. After walking quarter circle around the fountain I start walking a straight path. If Alan is facing South, which direction am I headed? Please respond only with \"North\", \"South\", \"East\", or \"West\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "North"} {"input": [{"role": "user", "content": "I face a circular fountain in such a way that a statue of Alan Turing at the center of the fountain faces me. I walk straight towards the fountain until I reach its edge. I then start walking clockwise along the edge of the fountain. After walking half circle around the fountain I start walking a straight path. If Alan is facing West, which direction am I headed? Please respond only with \"North\", \"South\", \"East\", or \"West\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "South"} {"input": [{"role": "user", "content": "I am walking a straight path in a courtyard as the sun is setting. I see a bird fly towards the sun. The bird came from my right and our paths are perpendicular. Which direction am I headed? Please respond only with \"South\". \"East\", \"North\" or \"West\"."}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "North"} {"input": [{"role": "user", "content": "I am walking a straight path in a courtyard as the sun is setting. I see a bird fly away from the sun. The bird came from my left and our paths are perpendicular. Which direction am I headed? Please respond only with \"South\". \"East\", \"North\" or \"West\"."}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "North"} {"input": [{"role": "user", "content": "I am walking a straight path in a courtyard as the sun is setting. I see a bird fly away from the sun. The bird came from my right and our paths are perpendicular. Which direction am I headed? Please respond only with \"South\". \"East\", \"North\" or \"West\"."}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "South"} {"input": [{"role": "user", "content": "I am walking a straight path in a courtyard as the sun is setting. I see a bird fly towards the sun. The bird came from my left and our paths are perpendicular. Which direction am I headed? Please respond only with \"South\". \"East\", \"North\" or \"West\"."}, {"role":"system", "content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "South"} ``` </details>
Linmj-Judy
pushed a commit
to TablewareBox/evals
that referenced
this pull request
Feb 27, 2024
# Thank you for contributing an eval!♥️ 🚨 Please make sure your PR follows these guidelines, **failure to follow the guidelines below will result in the PR being closed automatically**. Note that even if the criteria are met, that does not guarantee the PR will be merged nor GPT-4 access be granted. 🚨 **PLEASE READ THIS**: In order for a PR to be merged, it must fail on GPT-4. We are aware that right now, users do not have access, so you will not be able to tell if the eval fails or not. Please run your eval with GPT-3.5-Turbo, but keep in mind as we run the eval, if GPT-4 gets higher than 90% on the eval, we will likely reject it since GPT-4 is already capable of completing the task. We plan to roll out a way for users submitting evals to see the eval performance on GPT-4 soon. Stay tuned! Until then, you will not be able to see the eval performance on GPT-4. **Starting April 10, the minimum eval count is 15 samples, we hope this makes it easier to create and contribute evals.** Also, please note that we're using **Git LFS** for storing the JSON files, so please make sure that you move the JSON file to Git LFS before submitting a PR. Details on how to use Git LFS are available [here](https://git-lfs.com). ## Eval details 📑 ### Eval name 3D Globe Movement ### Eval description This eval tests an LLMs ability to understand 3D movement through space, in particular movement on or through planet Earth. Each example provides a starting point and a path consisting of one or two movements, and the expected answer is a state/province or ocean. Similar to the evals from openai#462 and openai#1060, this eval shows how difficult movement is for LLMs to understand, and builds upon those by showing how the problem is seemingly magnified by 3D movement and/or by requesting a region as answer rather than numerical positions. Testing on gpt-3.5-turbo, accuracy ranges from ~0.24 to ~0.31 ### What makes this a useful eval? This eval demonstrates that a long series of steps is not necessary in order to create a path that GPT is unable to follow, and that a simple trip to the planet's core and back again, with a slight offset in any direction, will often get it lost. Whereas it can often handle "travel 15 degrees East", hiding that actual travel behind a 2-step 3D path significantly hurts the model's performance. Interestingly, this eval seems to demonstrate the statistical rather than reasoning nature of GPT, as regardless of starting point or path, it shows a bias towards answering with oceans, especially the Pacific Ocean. ## Criteria for a good eval ✅ Below are some of the criteria we look for in a good eval. In general, we are seeking cases where the model does not do a good job despite being capable of generating a good response (note that there are some things large language models cannot do, so those would not make good evals). Your eval should be: - [x] Thematically consistent: The eval should be thematically consistent. We'd like to see a number of prompts all demonstrating some particular failure mode. For example, we can create an eval on cases where the model fails to reason about the physical world. - [x] Contains failures where a human can do the task, but either GPT-4 or GPT-3.5-Turbo could not. - [x] Includes good signal around what is the right behavior. This means either a correct answer for `Basic` evals or the `Fact` Model-graded eval, or an exhaustive rubric for evaluating answers for the `Criteria` Model-graded eval. - [x] **Include at least 15 high-quality examples.** If there is anything else that makes your eval worth including, please document it below. ### Unique eval value > Insert what makes your eval high quality that was not mentioned above. (Not required) ## Eval structure 🏗️ Your eval should - [x] Check that your data is in `evals/registry/data/{name}` - [x] Check that your YAML is registered at `evals/registry/evals/{name}.yaml` - [x] Ensure you have the right to use the data you submit via this eval (For now, we will only be approving evals that use one of the existing eval classes. You may still write custom eval classes for your own cases, and we may consider merging them in the future.) ## Final checklist 👀 ### Submission agreement By contributing to Evals, you are agreeing to make your evaluation logic and data under the same MIT license as this repository. You must have adequate rights to upload any data used in an Eval. OpenAI reserves the right to use this data in future service improvements to our product. Contributions to OpenAI Evals will be subject to our usual Usage Policies (<https://platform.openai.com/docs/usage-policies>). - [x] I agree that my submission will be made available under an MIT license and complies with OpenAI's usage policies. ### Email address validation If your submission is accepted, we will be granting GPT-4 access to a limited number of contributors. Access will be given to the email address associated with the merged pull request. - [x] I acknowledge that GPT-4 access will only be granted, if applicable, to the email address used for my merged pull request. ### Limited availability acknowledgment We know that you might be excited to contribute to OpenAI's mission, help improve our models, and gain access to GPT-4. However, due to the requirements mentioned above and the high volume of submissions, we will not be able to accept all submissions and thus not grant everyone who opens a PR GPT-4 access. We know this is disappointing, but we hope to set the right expectation before you open this PR. - [x] I understand that opening a PR, even if it meets the requirements above, does not guarantee the PR will be merged nor GPT-4 access be granted. ### Submit eval - [x] I have filled out all required fields of this form - [x] I have used **Git LFS** for the Eval JSON data - [x] (Ignore if not submitting code) I have run `pip install pre-commit; pre-commit install` and have verified that `black`, `isort`, and `autoflake` are running when I commit and push Failure to fill out all required fields will result in the PR being closed. ### Eval JSON data Since we are using Git LFS, we are asking eval submitters to add in as many Eval Samples (at least 5) from their contribution here: <details> <summary>View evals in JSON</summary> ### Eval ```jsonl {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 15 degree offset to the East"}], "ideal": "Colorado"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel due East 15 degrees"}], "ideal": "Colorado"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel due East 0.1 degrees"}], "ideal": "California"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel due East 1 meter"}], "ideal": "California"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel 0 meter"}], "ideal": "California"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and make one complete revolution around the planet"}], "ideal": "California"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 1 degree offset to the East"}], "ideal": "California"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 0.1 degree offset to the East"}], "ideal": "California"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 0.01 degree offset to the East"}], "ideal": "California"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 1 degree offset to the West"}], "ideal": "Pacific Ocean"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 90 degree offset to the East"}], "ideal": "Atlantic Ocean"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 180 degree offset to the East"}], "ideal": "Ahal"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of San Francisco and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 1 degree offset to the North"}], "ideal": "California"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of Kansas City and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 15 degree offset to the East"}], "ideal": "West Virginia"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of Kansas City and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 15 degree offset to the West"}], "ideal": "Utah"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 1 degree offset to the East"}], "ideal": "Atlantic Ocean"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel due East 10 degrees"}], "ideal": "Atlantic Ocean"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel due East 500 kilometers"}], "ideal": "Atlantic Ocean"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 1 degree offset to the West"}], "ideal": "New Jersey"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 10 degree offset to the West"}], "ideal": "Ohio"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel due West 10 degrees"}], "ideal": "Ohio"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel due West 15 degrees"}], "ideal": "Illinois"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel due West 25 degrees"}], "ideal": "Nebraska"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel due West 30 degrees"}], "ideal": "Colorado"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of New York City and travel due West 35 degrees"}], "ideal": "Colorado"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of Oklahoma City and travel directly downwards to the center of the Earth, then straight up, back to the surface, at a 0.1 degree offset to the East"}], "ideal": "Oklahoma"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of Oklahoma City and travel directly downwards to the center of the Earth, then straight up, back to the surface along the same path that was traveled downards."}], "ideal": "Oklahoma"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of Oklahoma City and travel directly downwards to the center of the Earth, then continue onwards to the other side of the planet"}], "ideal": "Xinjiang"} {"input": [{"role": "system", "content": "Pretend you are 3DPathGPT, a model that can accurately track 3D paths on, around, and through planet Earth based on plain language descriptions. For each path, determine the state, province, or ocean of the final destination. You may assume the object traveling the path encounters no resistance, such as if it were a neutrino. Try reasoning through the 3D path one step at a time, and at the end, provide the final answer enclosed in square brackets like [Europe]. Start at the center of Oklahoma City and travel directly downwards through to the other side of the Earth"}], "ideal": "Xinjiang"} ``` </details>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Thank you for contributing an eval!♥️
🚨 Please make sure your PR follows these guidelines, failure to follow the guidelines below will result in the PR being closed automatically. Note that even if the criteria are met, that does not guarantee the PR will be merged nor GPT-4 access granted. 🚨
PLEASE READ THIS:
In order for a PR to be merged, it must fail on GPT-4. We are aware that right now, users do not have access, so you will not be able to tell if the eval fails or not. Please run your eval with GPT-3.5-Turbo, but keep in mind as we run the eval, if GPT-4 gets higher than 90% on the eval, we will likely reject since GPT-4 is already capable of completing the task.
We plan to roll out a way for users submitting evals to see the eval performance on GPT-4 soon. Stay tuned! Until then, you will not be able to see the eval performance on GPT-4. Starting April 10, the minimum eval count is 15 samples, we hope this makes it easier to create and contribute evals.
Also, pelase note that we're using Git LFS for storing the JSON files, so please make sure that you move the JSON file to Git LFS before submitting a PR. Details on how to use Git LFS are available here.
Eval details 📑
Eval name
Cardinal Directions
Eval description
This eval tests the model's ability to make an internal representation of relative positions and reason about cardinal directions. It's a refinement of my previously submitted PR Relative Orientations (#1000 ), containing a handful of selected problems which make a more thematically consistent set of samples. Adjustments were made to improve the clarity, quality, as well as the diversity of parameters in the selected prompts for a more comprehensive assessment of problem-solving ability.
What makes this a useful eval?
It helps test the model's spatial reasoning ability
Criteria for a good eval ✅
Below are some of the criteria we look for in a good eval. In general, we are seeking cases where the model does not do a good job despite being capable of generating a good response (note that there are some things large language models cannot do, so those would not make good evals).
Your eval should be:
Basicevals or theFactModel-graded eval, or an exhaustive rubric for evaluating answers for theCriteriaModel-graded eval.If there is anything else that makes your eval worth including, please document it below.
Unique eval value
Eval structure 🏗️
Your eval should
evals/registry/data/{name}evals/registry/evals/{name}.yaml(For now, we will only be approving evals that use one of the existing eval classes. You may still write custom eval classes for your own cases, and we may consider merging them in the future.)
Final checklist 👀
Submission agreement
By contributing to Evals, you are agreeing to make your evaluation logic and data under the same MIT license as this repository. You must have adequate rights to upload any data used in an Eval. OpenAI reserves the right to use this data in future service improvements to our product. Contributions to OpenAI Evals will be subject to our usual Usage Policies (https://platform.openai.com/docs/usage-policies).
Email address validation
If your submission is accepted, we will be granting GPT-4 access to a limited number of contributors. Access will be given to the email address associated with the merged pull request.
Limited availability acknowledgement
We know that you might be excited to contribute to OpenAI's mission, help improve our models, and gain access to GPT-4. However, due to the requirements mentioned above and high volume of submissions, we will not be able to accept all submissions and thus not grant everyone who opens a PR GPT-4 access. We know this is disappointing, but we hope to set the right expectation before you open this PR.
Submit eval
pip install pre-commit; pre-commit installand have verified thatblack,isort, andautoflakeare running when I commit and pushFailure to fill out all required fields will result in the PR being closed.
Eval JSON data
Since we are using Git LFS, we are asking eval submitters to add in as many Eval Samples (at least 5) from their contribution here:
View evals in JSON
Eval
{"input": [{"role": "user", "content": "Chloe, Kate, Drew, and Mikey are gathered in a circle. Drew is opposite Chloe and Kate sees Chloe to her left. At the center is a bottle which points towards Mikey. When Chloe spins the bottle, it rotates two and three-quarters of a full circle. Who is the person opposite the direction the bottle is pointing? Please respond with only one of the following options: \"Chloe\", \"Mikey\", \"Drew\", \"Kate\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "Drew"} {"input": [{"role": "user", "content": "Daniel, Emily, Richard, and Max are gathered in a circle. Richard is opposite Daniel and Emily sees Daniel to her left. If Daniel points towards Max he points North West. If Emily points towards Richard what direction does she point? Please respond with only one of the following options: \"North\", \"South\", \"East\", \"West\", \"North East\", \"North West\", \"South East\", \"South West\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "North West"} {"input": [{"role": "user", "content": "Leonard, Marie, Carl, and Martin are gathered in a circle. Carl is opposite Leonard and Marie sees Leonard to her right. If Carl points towards Leonard, he points directly North. If Leonard points towards Martin, in what direction does he point? Please respond with only one of the following options: \"North\", \"South\", \"East\", \"West\", \"North East\", \"North West\", \"South East\", \"South West\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "South West"} {"input": [{"role": "user", "content": "Two perpendicular paths intersect at a cross. There is a banana peel along one path away from the intersection. Drew is walking directly North along one path when he sees the banana peel to his right. Frank sees Drew ahead of him as they both move towards the intersection. When Frank takes a turn at the intersection he avoids the banana peel by walking around it. In which direction did Frank turn at the intersection? Please respond with only one of the following options: \"North\", \"South\", \"East\", \"West\", \"North East\", \"North West\", \"South East\", \"South West\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "East"} {"input": [{"role": "user", "content": "Two perpendicular paths intersect in a cross. Alan walks along one path while Gordon walks along the other. Gordon is walking directly North. As they both move towards the intersection, Gordon sees Alan to his left. What direction is Gordon headed? Please respond with only one of the following options: \"North\", \"South\", \"West\", \"East\", \"North West\", \"North East\", \"South West\", \"South East\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "West"} {"input": [{"role": "user", "content": "Two birds are flying in perpendicular paths. One bird is flying Northward and the other Eastward. As Will is walking a straight path, he sees both birds on his right moving away from each other. Which direction is Will headed? Please respond with only one of the following options: \"North\", \"South\", \"East\", \"West\", \"North East\", \"North West\", \"South East\", \"South West\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "North West"} {"input": [{"role": "user", "content": "Two birds are flying in perpendicular paths. One bird is flying Southward and the other Westward. As Ryan is walking a straight path, he sees both birds on his left moving away from each other. Which direction is Ryan headed? Please respond with only one of the following options: \"North\", \"South\", \"East\", \"West\", \"North East\", \"North West\", \"South East\", \"South West\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "North West"} {"input": [{"role": "user", "content": "I face a circular fountain in such a way that a statue of Alan Turing at the center of the fountain faces me. I walk straight towards the fountain until I reach its edge. I then start walking counter-clockwise along the edge of the fountain. After walking three-quarters of a circle around the fountain I start walking a straight path. If Alan is facing North, which direction am I headed? Please respond only with \"North\", \"South\", \"West\", or \"East\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "North"} {"input": [{"role": "user", "content": "I face a circular fountain in such a way that a statue of Alan Turing at the center of the fountain faces me. I walk straight towards the fountain until I reach its edge. I then start walking counter-clockwise along the edge of the fountain. After walking full circle around the fountain I start walking a straight path. If Alan is facing East, which direction am I headed? Please respond only with \"North\", \"South\", \"West\", or \"East\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "North"} {"input": [{"role": "user", "content": "I face a circular fountain in such a way that a statue of Alan Turing at the center of the fountain faces me. I walk straight towards the fountain until I reach its edge. I then start walking clockwise along the edge of the fountain. After walking quarter circle around the fountain I start walking a straight path. If Alan is facing South, which direction am I headed? Please respond only with \"North\", \"South\", \"East\", or \"West\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "North"} {"input": [{"role": "user", "content": "I face a circular fountain in such a way that a statue of Alan Turing at the center of the fountain faces me. I walk straight towards the fountain until I reach its edge. I then start walking clockwise along the edge of the fountain. After walking half circle around the fountain I start walking a straight path. If Alan is facing West, which direction am I headed? Please respond only with \"North\", \"South\", \"East\", or \"West\""}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "South"} {"input": [{"role": "user", "content": "I am walking a straight path in a courtyard as the sun is setting. I see a bird fly towards the sun. The bird came from my right and our paths are perpendicular. Which direction am I headed? Please respond only with \"South\". \"East\", \"North\" or \"West\"."}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "North"} {"input": [{"role": "user", "content": "I am walking a straight path in a courtyard as the sun is setting. I see a bird fly away from the sun. The bird came from my left and our paths are perpendicular. Which direction am I headed? Please respond only with \"South\". \"East\", \"North\" or \"West\"."}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "North"} {"input": [{"role": "user", "content": "I am walking a straight path in a courtyard as the sun is setting. I see a bird fly away from the sun. The bird came from my right and our paths are perpendicular. Which direction am I headed? Please respond only with \"South\". \"East\", \"North\" or \"West\"."}, {"role":"system","content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "South"} {"input": [{"role": "user", "content": "I am walking a straight path in a courtyard as the sun is setting. I see a bird fly towards the sun. The bird came from my left and our paths are perpendicular. Which direction am I headed? Please respond only with \"South\". \"East\", \"North\" or \"West\"."}, {"role":"system", "content":"Do not provide any information apart from the answer. Do not include punctuations in the answer."}], "ideal": "South"}