Causal Language Modeling on M2D2 (test)
100Accuracy (Coding)
Coding expert
Updated 18d ago
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
2026.03 | 100 | 66.8 | 78.1 | 79.2 | 81.1 | 81 | |
2026.03 | 95.9 | 87.3 | 95.1 | 97.1 | 98.6 | 94.8 | |
2026.03 | 94.5 | 82.3 | 92.2 | 96.9 | 98.2 | 92.8 | |
2026.03 | 94.1 | 85.6 | 94 | 97.6 | 98.4 | 93.9 | |
2026.03 | 91.7 | 85.7 | 89.9 | 95.5 | 96.6 | 91.9 | |
2026.03 | 89.9 | 100 | 75.2 | 69.4 | 71.4 | 81.2 | |
2026.03 | 86.8 | 63.1 | 83.7 | 90.4 | 93.1 | 83.4 | |
2026.03 | 86.3 | 62.8 | 82.4 | 88.7 | 91.5 | 82.4 | |
2026.03 | 80.2 | 58.8 | 100 | 80 | 81.8 | 80.2 | |
2026.03 | 66.9 | 40.2 | 66.3 | 95.3 | 100 | 73.7 | |
2026.03 | 63.8 | 36.8 | 64.7 | 100 | 98 | 72.7 |