Inference
SWE-bench team

SWE-bench Multimodal · swebench.com

Resolved-issue rate on real GitHub issues, as published by the SWE-bench team.

ModelsModels with a result.8
Top resultBest result on this test.N/A
Top-3 spreadPoints from first to third.N/A
UpdatedDate the source changed the results.17 Nov 2025

Result and price

020406080100$3$10$30RESULTOUTPUT PRICE PER 1M TOKENS · LOG SCALE

Results

8 results
#ModelResultThe score from the source.
—o3GUIRepair36.0%
—Claude Sonnet 4OpenHands-Versa34.4%
—o4-mini (high)GUIRepair33.9%
—GPT-4.1GUIRepair31.1%
—Claude 3.7 SonnetOpenHands-Versa30.9%
—Claude Sonnet 3.5SWE-agent12.1%
—GPT-4oSWE-agent10.6%
—Claude 3.5 SonnetSWE-agent Multimodal8.8%