Medical Question Answering on MedQA (held-out)
10SC@10 ScoreSelf-Consistency
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Self-ConsistencyModel=Gemini 3.1 Pro2026.05 | 10 | — | — | |
| Self-ConsistencyModel=Claude Sonnet 4.62026.05 | 10 | — | — | |
| GEOModel=Gemini 3.1 Pro2026.05 | — | 82.7 | 0.184 | |
| GEOModel=Claude Sonnet 4.62026.05 | — | 75.9 | 0.047 |