Mathematical Reasoning on FrontierMath T1-3
37.6ScoreGemini-3-Pro
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini-3-ProEvaluation protocol=Avg@82026.02 | 37.6 | |
| GPT-5Evaluation protocol=Avg@82026.02 | 32.4 | |
| Claude-Opus-4.5Evaluation protocol=Avg@82026.02 | 20.7 |
Loading the SOTA2 catalog…