Mathematical Problem Solving on BeyondAIME
86.5ScoreSeed2.0 Pro
Evaluation Results
| Method | Links | |
|---|---|---|
| Seed2.0 Pro2026.06 | 86.5 | |
| GPT-5.2 High2026.06 | 86 | |
| Gemini-3-pro High2026.06 | 83 | |
| Gemini-3-FlashTier=High2026.06 | 82 | |
| Seed2.0 Lite2026.06 | 76 | |
| GPT-5-miniTier=High2026.06 | 72 | |
| Seed2.0 Mini2026.06 | 69 | |
| Claude-Opus-4.52026.06 | 69 | |
| Claude-Sonnet-4.52026.06 | 57 |