Mathematics on GSM8K (test)
84.99Accuracy
Qwen3-4B-Base
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.06 | 84.99 | |
2026.06 | 84.15 | |
2026.06 | 83.55 | |
2026.06 | 81 | |
2026.06 | 80.44 | |
2026.06 | 79.83 | |
2026.06 | 79.1 | |
2026.06 | 77.33 | |
2026.06 | 74.37 | |
2026.06 | 66.41 | |
2026.06 | 63.1 |