List your company

Radiology Report Evaluation on RaTE-Eval

0.4493GREEN ScoreClaude Opus 4.6
0.0501480.1537740.25740.361026Apr 3, 2026

Evaluation results

MethodLinks
Claude Opus 4.6Reasoning / Thinking effort=low2026.040.44930.24070.40670.46330.39
Claude Sonnet 4.6Reasoning / Thinking effort=low2026.040.43220.24610.37820.45260.3773
GPT-4.1 mini2026.040.41950.19660.33690.44740.3501
GPT-4.1 nano2026.040.39140.19010.27540.5040.3402
GPT-4.12026.040.36540.22220.3350.45180.3436
GPT-5Reasoning / Thinking effort=low2026.040.34950.22080.29020.32960.2975
GPT-5 miniReasoning / Thinking effort=low2026.040.33330.13820.29430.40910.2937
Qwen3 30BReasoning / Thinking effort=thinking, Quantization=FP82026.040.28510.05860.19780.20920.1877
Gemini3 FlashReasoning / Thinking effort=low2026.040.06550.00610.46410.16170.1744