Benchmark
SWE-bench Verified (Agentic Coding)
SWE-bench Verified is a human-filtered subset of 500 software engineering problems drawn from real GitHub issues across 12 popular Python repositories…
- Modality
- text
- Categories
- reasoning, code
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 2
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Claude Sonnet 4.5 | Anthropic | 0.772 | 2025-09-29 | evidence |
| Kimi K2 Instruct | Moonshot AI | 0.658 | 2025-07-11 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.