List your company

Feasibility Prediction on SWE-bench

47.6F1@1Qwen3 235B
31.58435.74239.944.058May 29, 2026

Evaluation results

MethodLinks
Qwen3 235B2026.0547.635.132.8
GPT-5.2 Instant2026.0543.540.221.2
Claude Opus 4.72026.0541.151.148.8
Gemini 3.1 Pro Preview2026.0539.258.252
Claude Sonnet 4.62026.0532.237.723.4