Common Sense Reasoning on ARC-C
86Accuracy
Qwen-2.5-7B
Updated 8d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.05 | 86 | 74.8 | |
| 84.5 | 53.5 | ||
2026.05 | 83.3 | 40.3 | |
2026.05 | 81 | 49.8 | |
| 80.7 | 46.8 | ||
2026.05 | 80.5 | 42.2 | |
2026.05 | 63.1 | 56.4 | |
| 62.6 | 36.6 | ||
| 62.4 | 24.5 | ||
2026.05 | 62.2 | -26 | |
2026.05 | 61.9 | 31.4 | |
2026.05 | 61.7 | 56.5 | |
| 61.1 | 46.5 | ||
2026.05 | 61 | 20.7 | |
2026.05 | 60.9 | 14 | |
2026.05 | 59.2 | 37.9 | |
| 58.8 | 23.5 | ||
2026.05 | 58.1 | 30.1 |