{"id":19562354,"url":"https://github.com/openinterpreter/benchmarks-v0","last_synced_at":"2025-04-27T00:31:33.118Z","repository":{"id":241185978,"uuid":"804574362","full_name":"OpenInterpreter/benchmarks-v0","owner":"OpenInterpreter","description":null,"archived":false,"fork":false,"pushed_at":"2024-07-11T06:01:50.000Z","size":125,"stargazers_count":5,"open_issues_count":0,"forks_count":2,"subscribers_count":1,"default_branch":"main","last_synced_at":"2024-07-11T07:31:57.313Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"agpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/OpenInterpreter.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"docs/CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-05-22T21:09:28.000Z","updated_at":"2024-07-11T07:32:09.299Z","dependencies_parsed_at":"2024-05-22T22:30:29.802Z","dependency_job_id":"f6fd24ed-6780-43a7-a185-489c232d2703","html_url":"https://github.com/OpenInterpreter/benchmarks-v0","commit_stats":null,"previous_names":["imapersonman/oi-benchmarks","openinterpreter/benchmarks","openinterpreter/benchmarks-v0"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OpenInterpreter%2Fbenchmarks-v0","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OpenInterpreter%2Fbenchmarks-v0/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OpenInterpreter%2Fbenchmarks-v0/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OpenInterpreter%2Fbenchmarks-v0/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/OpenInterpreter","download_url":"https://codeload.github.com/OpenInterpreter/benchmarks-v0/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251072279,"owners_count":21532004,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-11-11T05:14:19.399Z","updated_at":"2025-04-27T00:31:32.865Z","avatar_url":"https://github.com/OpenInterpreter.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"This repo is used to run various AI benchmarks on [Open Interpreter](https://github.com/OpenInterpreter/open-interpreter).\n\nThere is currently support for [GAIA](https://huggingface.co/gaia-benchmark) and [SWE-bench](https://www.swebench.com/)\n\n---\n\n## Setup\n\n1. Make sure the following software is installed on your computer.\n\n- [Git](https://git-scm.com)\n- [Git-LFS](https://git-lfs.com)\n- [Python](https://www.python.org)\n- [Docker](https://www.docker.com/)\n\n2. Run Docker\n\n3. Copy-paste the following into your terminal\n\n```bash\ngit clone https://github.com/OpenInterpreter/benchmarks.git \\\n  \u0026\u0026 cd benchmarks \\\n  \u0026\u0026 python -m venv .venv \\\n  \u0026\u0026 source .venv/bin/activate \\\n  \u0026\u0026 python -m pip install -r requirements.txt \\\n  \u0026\u0026 docker build -t worker . \\\n  \u0026\u0026 python setup.py\n```\n\n4. Enter your [Huggingface token](https://huggingface.co/settings/tokens)\n\n## Running Benchmarks\n\nThis section assumes:\n\n- `benchmarks` (downloaded via git in the preview section) is set as the current working directory.\n- You've activated the virtualenv with the installed prerequisite packages.\n- If using an OpenAI model, your `OPENAI_API_KEY` environment variable is set with a valid OpenAI API key.\n- If using a Groq model, your `GROQ_API_KEY` environment variable is set with a valid Groq API key.\n\nNote: For running GAIA, you have to accept the conditions to access its files and content on [Huggingface](https://huggingface.co/datasets/gaia-benchmark/GAIA)\n\n### Example: gpt-3.5-turbo, first 16 GAIA tasks, 8 docker containers\n\nThis command will output a file called `output.csv` containing the results of the benchmark.\n\n```bash\npython run_benchmarks.py \\\n  --command gpt35turbo \\\n  --ntasks 16 \\\n  --nworkers 8\n```\n\n- `--command gpt35turbo`: Replace gpt35turbo with any existing key in the commands `Dict` in commands.py. Defaults to gpt35turbo.\n- `--ntasks 16`: Grabs the first 16 GAIA tasks to run. Defaults to all 165 GAIA validation tasks.\n- `--nworkers 8`: Number of docker containers to run at once. Defaults to whatever max_workers defaults to when constructing a ThreadPoolExecutor.\n\n## Troubleshooting\n\n- `ModuleNotFoundError: No module named '_lzma'` when running example.\n  - If you're using `pyenv` to manage python versions, [this stackoverflow post](https://stackoverflow.com/questions/59690698/modulenotfounderror-no-module-named-lzma-when-building-python-using-pyenv-on) might help.\n- `ModuleNotFoundError: No module named 'pkg_resources'` when running example.\n  - Refer to [this stackoverflow post](https://stackoverflow.com/questions/7446187/no-module-named-pkg-resources) for now.\n  - OpenInterpreter should probably include `setuptools` in its list of dependencies, or should switch to another module that's in python's standard library.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fopeninterpreter%2Fbenchmarks-v0","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fopeninterpreter%2Fbenchmarks-v0","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fopeninterpreter%2Fbenchmarks-v0/lists"}