Instruction Tuning on TyDiQA, MMLU, and BBH Aggregate
57.6TyDiQA Score
SEED
Updated 16d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.05 | 57.6 | 65.1 | 66.9 | 57.3 | |
2026.05 | 56.1 | 66.6 | 69.9 | 58.2 | |
2026.05 | 55.9 | 64.4 | 66.1 | 56.2 | |
2026.05 | 55.7 | 64.5 | 66.1 | 56.4 | |
2026.05 | 55.4 | 64.4 | 65.7 | 55.9 | |
2026.05 | 55.4 | 65.1 | 67.4 | 56.8 | |
2026.05 | 55.2 | 64.7 | 66 | 56.2 | |
2026.05 | 55.1 | 65.1 | 67.3 | 57.3 | |
2026.05 | 55 | 65.4 | 68.1 | 57.2 | |
2026.05 | 54.8 | 64.2 | 65 | 55.6 | |
2026.05 | 54.7 | 65.5 | 67.3 | 56.6 | |
2026.05 | 54.6 | 65.8 | 68.2 | 57.1 | |
2026.05 | 54.4 | 69 | 74.3 | 57.2 | |
2026.05 | 54.4 | 70.4 | 75.9 | 58.2 | |
2026.05 | 54.1 | 65.6 | 67.8 | 56.5 | |
2026.05 | 53.3 | 69.2 | 73.6 | 56.8 | |
2026.05 | 53.1 | 69.3 | 74.2 | 57.1 | |
2026.05 | 52.6 | 69 | 73.8 | 56.5 | |
2026.05 | 52.3 | 65.3 | 66.3 | 56 | |
2026.05 | 52.3 | 68.9 | 74 | 56.6 | |
2026.05 | 52 | 68.7 | 73.9 | 56 | |
2026.05 | 51.6 | 64 | 63.1 | 54.6 | |
2026.05 | 50.6 | 69.5 | 72.6 | 57.3 | |
2026.05 | 50.2 | 68.5 | 70.8 | 56.2 | |
2026.05 | 49.9 | 69.1 | 71.3 | 56.4 | |
2026.05 | 49.6 | 68.8 | 70.6 | 55.9 | |
2026.05 | 49.6 | 69 | 71 | 56.2 | |
2026.05 | 49.5 | 70 | 72.9 | 57.3 | |
2026.05 | 49.3 | 68.5 | 70.4 | 55.6 | |
2026.05 | 48.5 | 68.7 | 70.3 | 54.6 | |
2026.05 | 47.4 | 67.9 | 70 | 53 | |
2026.05 | 47.3 | 63.3 | 62.2 | 53 | |
2026.05 | 42.5 | 46.9 | 41.4 | 58.2 | |
2026.05 | 41.9 | 49.6 | 41.9 | 57.3 | |
2026.05 | 40.9 | 47 | 41 | 57.2 | |
2026.05 | 40.8 | 46.5 | 41.5 | 57.1 | |
2026.05 | 40.5 | 50.4 | 44.8 | 57.3 | |
2026.05 | 40.3 | 45.8 | 40.1 | 56.5 | |
2026.05 | 40.1 | 46.2 | 40.7 | 56.8 | |
2026.05 | 40 | 46.3 | 40.6 | 56.6 | |
2026.05 | 39.9 | 49 | 41.3 | 56.2 | |
2026.05 | 39.7 | 49.5 | 40.9 | 56.2 | |
2026.05 | 39.6 | 50.1 | 41.5 | 56.4 | |
2026.05 | 39.6 | 46.1 | 39.8 | 56 | |
2026.05 | 39.3 | 49.3 | 40.6 | 55.9 | |
2026.05 | 39 | 48.9 | 40.3 | 55.6 | |
2026.05 | 38.5 | 46.8 | 40 | 54.6 | |
2026.05 | 32.8 | 45.7 | 39.5 | 53 |