SWE-bench

SWE-bench: Can Language Models Resolve Real-World GitHub Issues?

↓ SWE-bench Verified

2,294 个任务实例,基于 12 个流行 Python 代码库中的真实 GitHub issue 及其对应的修复 pull request 构建。给定 issue 文本和代码库快照,智能体需生成补丁;通过运行该 PR 的 FAIL_TO_PASS 和 PASS_TO_PASS 单元测试评分。是最初的智能体编程基准,也是 Verified、Lite、Multimodal、Multilingual 和 Pro 等后续版本的模板。

52.62%
Sonar Foundation Agent + Claude 4.5 Opus
官方榜单
2023-10-10 → 2025-12-19: 1.96% → 52.62%
发布
2023-10
维护者
Princeton NLP / SWE-bench team (Jimenez et al.)
状态
saturated
污染风险
high
指标
% resolved (percent, ↑)
题量
2,294
领域
software-engineering code tool-use
人类
无实测基线

备注. The full 2,294-instance set contains under-specified and untestable tasks (the reason OpenAI and the maintainers curated SWE-bench Verified). Almost all frontier evaluation moved to Verified after August 2024; the Full leaderboard still accepts submissions but receives few, so treat it as historical.

完整账本

系统开发者分数日期来源条件
Sonar Foundation Agent + Claude 4.5 OpusAnthropic52.62%官方榜单split: full scaffold: Sonar Foundation Agent
Top of the Full leaderboard; submission not run or checked by the SWE-bench team.
SWE-agent 1.0 (Claude 3.7 Sonnet)Anthropic33.83%官方榜单split: full scaffold: SWE-agent 1.0
OpenHands + CodeAct v2.1 (claude-3-5-sonnet-20241022)Anthropic29.38%官方榜单split: full scaffold: OpenHands CodeAct v2.1
SWE-agent + GPT 4 (1106)OpenAI12.47%官方榜单split: full scaffold: SWE-agent
RAG + Claude 2Anthropic1.96%官方榜单split: full scaffold: RAG baseline
Paper baseline (BM25 retrieval, no agent), checked by the SWE-bench team.