Radiology Report Evaluation on RadEval Error Annotations (test)
33.22GREENGREEN
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| GREENModel=GPT-4.1 mini, Prompt Mode=zero-shot2026.04 | 33.22 | — | — | — | — | — | |
| GREENModel=Claude Sonnet 4.6 (low), Prompt Mode=zero-shot2026.04 | 29.31 | — | — | — | — | — | |
| GREENModel=Gemini 3 Flash (low), Prompt Mode=zero-shot2026.04 | 16.75 | — | — | — | — | — | |
| FineRadScoreModel=GPT-4.1 mini, Prompt Mode=zero-shot2026.04 | — | — | — | — | 17.25 | — | |
| FineRadScoreModel=Gemini 3 Flash (low), Prompt Mode=zero-shot2026.04 | — | — | — | — | 18.1 | — | |
| FineRadScoreModel=Claude Sonnet 4.6 (low), Prompt Mode=zero-shot2026.04 | — | — | — | — | 23.33 | — | |
| GREEN F1Model=GPT-4.1 mini, Prompt Mode=zero-shot2026.04 | — | — | — | 44.41 | — | — | |
| GREEN F1Model=Gemini 3 Flash (low), Prompt Mode=zero-shot2026.04 | — | — | — | 41.03 | — | — | |
| GREEN F1Model=Claude Sonnet 4.6 (low), Prompt Mode=zero-shot2026.04 | — | — | — | 39.24 | — | — | |
| GREEN-ECModel=GPT-4.1 mini, Prompt Mode=zero-shot2026.04 | — | — | 56.06 | — | — | — | |
| GREEN-ECModel=Gemini 3 Flash (low), Prompt Mode=zero-shot2026.04 | — | — | 2.06 | — | — | — | |
| GREEN-ECModel=Claude Sonnet 4.6 (low), Prompt Mode=zero-shot2026.04 | — | — | 51.03 | — | — | — | |
| RadFactModel=GPT-4.1 mini, Prompt Mode=zero-shot2026.04 | — | 29.46 | — | — | — | — | |
| VERTModel=GPT-4.1 mini, Prompt Mode=zero-shot2026.04 | — | — | — | — | — | 37.1 | |
| VERTModel=Gemini 3 Flash (low), Prompt Mode=zero-shot2026.04 | — | — | — | — | — | 19.37 | |
| VERTModel=Claude Sonnet 4.6 (low), Prompt Mode=zero-shot2026.04 | — | — | — | — | — | 32.91 |