Language Modeling on Broad evaluation suite unseen S1 (dev)
74.2Average Accuracy
all-FA
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.04 | 74.2 | 100 | 1 | |
2026.04 | 71.8 | 97 | 2 | |
2026.04 | 71.1 | 96 | 2.9 | |
2026.04 | 69.7 | 94 | 4.8 | |
2026.04 | 66.8 | 90 | 6.2 | |
2026.04 | 65.3 | 88 | 6.1 | |
2026.04 | 60.2 | 81 | 6.9 | |
2026.04 | 57.2 | 77 | 10.7 |