Mathematical Reasoning on GSM+ (Accuracy)
62.29Accuracy (GSM+)
Qwen-2.5-3B-instruct
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2025.07 | 62.29 | |
2025.07 | 62.27 | |
2025.07 | 61.94 | |
2025.07 | 55.33 | |
2025.07 | 55.11 | |
2025.07 | 54.37 | |
2026.05 | 50.2 | |
2026.05 | 42.4 | |
2026.05 | 42.3 | |
2025.07 | 37.88 | |
2025.07 | 37.28 | |
2025.07 | 36.5 | |
2026.05 | 28.9 | |
2026.05 | 28.1 | |
2026.05 | 27.8 | |
2026.05 | 26.6 | |
2026.05 | 26.5 | |
2026.05 | 25.2 | |
2026.05 | 25.1 | |
2026.05 | 17 | |
2026.05 | 4.6 | |
2026.05 | 4.3 |