Inference
EN

SWE-bench Verified (mini-swe-agent-v2)

ModelsModels with a result.5
Top resultBest result on this benchmark.75.6%Claude Opus 4.6
Top-3 spreadPoints from first to third.2.8 pts
YearYear of release.—

Result and price

5 of 5 results

Results

5 results
#ModelResultThe score from the source.
01Claude Opus 4.675.6%
02MiniMax M2.775.4%
03GLM-572.8%
04Kimi K2.570.8%
05Trinity-Large-Thinking63.2%