{"id":46277892,"url":"https://github.com/LiberCoders/FeatureBench","last_synced_at":"2026-03-17T23:01:18.891Z","repository":{"id":337817294,"uuid":"1138134975","full_name":"LiberCoders/FeatureBench","owner":"LiberCoders","description":"[ICLR 2026] Official Implementation of \"FeatureBench: Benchmarking Agentic Coding for Complex Feature Development\" ","archived":false,"fork":false,"pushed_at":"2026-03-03T04:07:15.000Z","size":13156,"stargazers_count":25,"open_issues_count":1,"forks_count":1,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-03-03T08:31:56.636Z","etag":null,"topics":["agentic-coding","benchmark","large-language-model","software-engineering"],"latest_commit_sha":null,"homepage":"https://LiberCoders.github.io/FeatureBench/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/LiberCoders.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"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,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-01-20T09:35:46.000Z","updated_at":"2026-03-03T04:07:18.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/LiberCoders/FeatureBench","commit_stats":null,"previous_names":["libercoders/featurebench"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/LiberCoders/FeatureBench","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LiberCoders%2FFeatureBench","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LiberCoders%2FFeatureBench/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LiberCoders%2FFeatureBench/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LiberCoders%2FFeatureBench/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/LiberCoders","download_url":"https://codeload.github.com/LiberCoders/FeatureBench/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LiberCoders%2FFeatureBench/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30635004,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-17T22:38:22.569Z","status":"ssl_error","status_checked_at":"2026-03-17T22:38:11.804Z","response_time":56,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["agentic-coding","benchmark","large-language-model","software-engineering"],"created_at":"2026-03-04T05:00:35.195Z","updated_at":"2026-03-17T23:01:18.884Z","avatar_url":"https://github.com/LiberCoders.png","language":"Python","funding_links":[],"categories":["Tools"],"sub_categories":["Benchmarking \u0026 Testing"],"readme":"\u003cp align=\"center\"\u003e\n  \u003cimg src=\"docs/pics/logo.png\" style=\"height: 10em\" alt=\"logo\" /\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://arxiv.org/abs/2602.10975\"\u003e\u003cimg src=\"https://img.shields.io/badge/arXiv-2602.10975-b31b1b.svg\" alt=\"arXiv\"\u003e\u003c/a\u003e\n  \u003ca href=\"LICENSE\"\u003e\u003cimg src=\"https://img.shields.io/badge/license-MIT-green.svg\" alt=\"License\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://hub.docker.com/u/libercoders\"\u003e\u003cimg src=\"https://img.shields.io/badge/DockerHub-Images-blue.svg\" alt=\"DockerHub\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://huggingface.co/datasets/LiberCoders/FeatureBench\"\u003e\u003cimg src=\"https://img.shields.io/badge/HuggingFace-datasets-yellow.svg\" alt=\"HuggingFace\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://LiberCoders.github.io/FeatureBench/\"\u003e\u003cimg src=\"https://img.shields.io/badge/Leaderboard-view-purple.svg\" alt=\"Leaderboard\"\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n---\n\nFeatureBench is a test-driven data generation and evaluation pipeline for feature-level coding benchmarks.\nIt provides a unified CLI to run inference, evaluation, and dataset generation.\n\n## 📰 News\n\n🎁 **2026.02.06**: We now support one-click inference for mainstream agent frameworks, including **OpenHands, Claude Code, Codex, Gemini CLI, and mini-swe-agent**. All supported agent frameworks can be found [here](featurebench/infer/agents/). We have also open-sourced the FeatureBench **data pipeline**.\n\n## 🚀 Quickstart\n\n**Prerequisites:**\n- [uv](https://docs.astral.sh/uv/getting-started/installation/) for Python environment management\n- [docker](https://docs.docker.com/engine/install/) for reproducible builds and evaluation\n\n```bash\n# pypi\npip install featurebench\n# or uv add featurebench\n\n# local\ngit clone https://github.com/LiberCoders/FeatureBench.git\ncd FeatureBench\nuv sync\nsource .venv/bin/activate\n```\n\n**Configure:**\n```bash\ncp config_example.toml config.toml\n```\nSee [docs/config.md](docs/config.md) for a comprehensive reference (harness, infer, data pipeline) with examples.\n\n**Optional: pre-pull images to reduce network variance:**\n```bash\nfb pull --mode lite                 # lite split image list (13 images)\nfb pull --mode full                 # full split image list (24 images)\nfb pull --mode /path/to/images.txt  # one image name per line\n\n# full list: featurebench/resources/constants/full_images.txt\n# lite list: featurebench/resources/constants/lite_images.txt\n```\n\n**Run inference:**\n```bash\nfb infer \\\n    --config-path config.toml \\\n    --agent mini_swe_agent \\\n    --model openai/qwen3-coder-480b-a35b-instruct \\\n    --split lite\n```\n\n**Run evaluation:**\n```bash\nfb eval \\\n    -p runs/\u003ctimestamp\u003e/output.jsonl \\\n    --split lite\n    # use -p gold to verify the gold patches\n```\n\n## 🧭 CLI Overview\n\n`fb` provides three core commands:\n- `fb infer` runs `featurebench.infer.run_infer` (docs: [docs/infer_cli_arg.md](docs/infer_cli_arg.md))\n- `fb eval` runs `featurebench.harness.run_evaluation` (docs: [docs/harness_cli_arg.md](docs/harness_cli_arg.md))\n- `fb data` runs `featurebench.pipeline` (docs: [docs/pipeline.md](docs/pipeline.md))\n\n## ✍️ Citation\n\nIf you found FeatureBench useful, please cite us as:\n\n```bibtex\n@article{zhou2026featurebench,\n  title={FeatureBench: Benchmarking Agentic Coding for Complex Feature Development},\n  author={Zhou, Qixing and Zhang, Jiacheng and Wang, Haiyang and Hao, Rui and Wang, Jiahe and Han, Minghao and Yang, Yuxue and Wu, Shuzhe and Pan, Feiyang and Fan, Lue and others},\n  journal={arXiv preprint arXiv:2602.10975},\n  year={2026}\n}\n```\n\n## 📧 Contact\n\nIf you have any questions, feel free to contact [qixingzhou1125@gmail.com](mailto:qixingzhou1125@gmail.com) or [zjcheng2022@gmail.com](mailto:zjcheng2022@gmail.com).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FLiberCoders%2FFeatureBench","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FLiberCoders%2FFeatureBench","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FLiberCoders%2FFeatureBench/lists"}