SWE-bench
Indexed results from SWE-bench. Each ranking retains its own metric and evaluation conditions.
SWE-bench Multimodal
sweBench · SWE-bench · Resolved tasks · percent
- OpenAI: o3openai35.98%
- Claude Sonnet 4anthropic34.43%
- OpenAI: o4 Mini (batch)openai33.85%
- OpenAI: GPT-4.1openai31.14%
- OpenAI: GPT-4oopenai11.99%
- OpenAI: GPT-4oopenai9.28%
Models
LoadingBenchmarks
Explore every benchmark
LoadingThese charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.