Algorithmic Reasoning on GSM8K (Accuracy)
92.6Accuracy
RM-Regen
Updated 25d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.03 | 92.6 | |
2026.03 | 92 | |
2026.03 | 91.2 | |
2026.03 | 90.2 | |
2026.03 | 89.8 | |
2026.03 | 89.6 | |
2026.03 | 89.6 | |
2026.03 | 89.6 | |
2026.03 | 88.8 | |
2026.03 | 88 | |
2026.03 | 87.2 | |
2026.03 | 87 | |
2026.03 | 85.8 | |
2026.03 | 85.6 | |
2026.03 | 85.4 | |
2026.03 | 84.6 | |
2026.03 | 83.6 | |
2026.03 | 83.4 | |
2026.03 | 80.8 | |
2026.03 | 80.2 | |
2026.03 | 75.6 | |
2026.03 | 70.4 | |
2026.03 | 40 |