Mathematical Reasoning on AIME 2026 (Accuracy, Drop, TC2b)
97.1Accuracy
VibeThinker-3B + CLR
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.06 | 97.1 | - | - | |
2026.06 | 95.8 | - | - | |
2026.06 | 95.3 | - | - | |
2026.06 | 95.1 | - | - | |
2026.06 | 94.3 | - | - | |
2026.06 | 94.2 | - | - | |
2026.06 | 93.3 | - | - | |
2026.06 | 93.2 | - | - | |
2026.06 | 91.7 | - | - | |
2026.06 | 91.3 | - | - | |
2026.06 | 89.8 | - | - | |
2026.06 | 70 | - | - | |
2026.06 | 40 | -53.33 | 66.67 | |
2026.06 | 36.67 | -53.33 | 66.67 | |
2026.06 | 16.67 | -53.33 | 66.67 | |
2026.06 | 16.67 | -53.33 | 66.67 |