Agent 评测
3 条SWE-bench 这类任务级评测。
| # | 仓库 | 分类 | Stars | 最近推送 |
|---|---|---|---|---|
| 1 | SWE-agent/SWE-agent SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024] | Agent 评测 | 21k | 2026-11-09 22:24 UTC |
| 2 | openai/evals Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks. | Agent 评测 | 20k | 2026-04-14 15:29 UTC |
| 3 | SWE-bench/SWE-bench SWE-bench: Can Language Models Resolve Real-world Github Issues? | Agent 评测 | 6.2k | 2026-09-18 05:08 UTC |