Mathematical Reasoning on AddSub (Accuracy Metrics)
85.6Accuracy
ExpertCondenser
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.04 | 85.6 | - | - | |
2026.04 | 79.5 | - | - | |
2026.04 | 72.8 | - | - | |
2026.04 | 68.8 | - | - | |
2026.04 | 63.4 | - | - | |
2026.04 | 61.8 | - | - | |
2026.04 | 60.8 | - | - | |
2026.04 | - | 59.4 | - | |
2026.04 | - | 81.7 | - | |
2026.04 | - | 76.6 | 61.7 | |
2026.04 | - | - | 62 | |
2026.04 | - | 87.9 | 64.8 | |
2026.04 | - | - | 8.3 |