Mathematical Reasoning on AIME '26 (Score)
90.2ScoreQwen3-Next-80B-A3B-Think
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3-Next-80B-A3B-ThinkActive=3B, Total=80B2026.05 | 90.2 | |
| Nemotron-3-Nano-30B-A3BActive=3B, Total=30B2026.05 | 90.1 | |
| ZAYA1-8BActive=0.7B, Total=8B2026.05 | 89.1 | |
| Mistral-Small-4-119BActive=6B, Total=119B2026.05 | 86.4 | |
| Intellect-3Active=12B, Total=106B2026.05 | 86.3 | |
| OLMo-3.1-32B-ThinkActive=32B, Total=32B2026.05 | 78.9 | |
| Arcee-Trinity-MiniActive=3B, Total=26B2026.05 | 59.6 |