List your company

Codebase QA on SWE-QA (test)

80.28ScoreGPT-4.1-mini
33.854445.907257.9670.0128Jan 29, 2026

Evaluation results

MethodLinks
GPT-4.1-miniSize=[10, 100]B, SWE Training Data=-2026.0180.28
SWE-SPOTSize=4B, SWE Training Data=8K trajs in one target repo2026.0178.05
Gemini-2.5-Flash-LiteSize=[0.1, 10]B, SWE Training Data=-2026.0173.36
CWM (Meta)Size=32B, SWE Training Data=3M trajs from 3.15K repos2026.0173.09
Qwen3-Coder-30BSize=32B, SWE Training Data=-2026.0165.48
Gemma-3-27b-itSize=27B, SWE Training Data=-2026.0165.19
Qwen3-4B-Instruct-2507Size=4B, SWE Training Data=-2026.0161.79
Mini-Coder-4BSize=4B, SWE Training Data=400K trajs from 128 repos2026.0157.3
GPT-5-nanoSize=[0.1, 10]B, SWE Training Data=-2026.0135.64