Mathematical Problem Solving on MathArenaApex
24.5ScoreGemini-3-pro High
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini-3-pro High2026.06 | 24.5 | |
| Seed2.0 Pro2026.06 | 20.3 | |
| GPT-5.2 High2026.06 | 18.2 | |
| Gemini-3-FlashTier=High2026.06 | 17.7 | |
| Seed2.0 Lite2026.06 | 4.7 | |
| Seed2.0 Mini2026.06 | 4.2 | |
| GPT-5-miniTier=High2026.06 | 2.1 | |
| Claude-Opus-4.52026.06 | 1.6 | |
| Claude-Sonnet-4.52026.06 | 1 |