Radiology Report Evaluation on RaTE-Eval
0.4493GREEN ScoreClaude Opus 4.6
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Claude Opus 4.6Reasoning / Thinking effort=low2026.04 | 0.4493 | 0.2407 | 0.4067 | 0.4633 | 0.39 | |
| Claude Sonnet 4.6Reasoning / Thinking effort=low2026.04 | 0.4322 | 0.2461 | 0.3782 | 0.4526 | 0.3773 | |
| GPT-4.1 mini2026.04 | 0.4195 | 0.1966 | 0.3369 | 0.4474 | 0.3501 | |
| GPT-4.1 nano2026.04 | 0.3914 | 0.1901 | 0.2754 | 0.504 | 0.3402 | |
| GPT-4.12026.04 | 0.3654 | 0.2222 | 0.335 | 0.4518 | 0.3436 | |
| GPT-5Reasoning / Thinking effort=low2026.04 | 0.3495 | 0.2208 | 0.2902 | 0.3296 | 0.2975 | |
| GPT-5 miniReasoning / Thinking effort=low2026.04 | 0.3333 | 0.1382 | 0.2943 | 0.4091 | 0.2937 | |
| Qwen3 30BReasoning / Thinking effort=thinking, Quantization=FP82026.04 | 0.2851 | 0.0586 | 0.1978 | 0.2092 | 0.1877 | |
| Gemini3 FlashReasoning / Thinking effort=low2026.04 | 0.0655 | 0.0061 | 0.4641 | 0.1617 | 0.1744 |