Research-Level Mathematical Proof Writing on EXPERTMATH
47.14ScoreGemini-3-Pro
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini-3-ProEvaluation protocol=Avg@82026.02 | 47.14 | |
| GPT-5Evaluation protocol=Avg@82026.02 | 35.71 | |
| Claude-Opus-4.5Evaluation protocol=Avg@82026.02 | 7.14 |