Social Commonsense Reasoning on SocialIQA
87.11Accuracy
Hard-routing MoE
Updated 18d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.02 | 87.11 | - | - | |
2026.02 | 85.52 | - | - | |
2026.02 | 83.96 | - | - | |
| 83.74 | - | - | ||
2026.02 | 83.4 | - | - | |
2026.02 | 83.04 | - | - | |
2026.03 | 82.91 | - | - | |
2026.03 | 82.69 | - | - | |
2026.03 | 81.63 | - | - | |
2026.02 | 80.99 | - | - | |
2026.03 | 80.6 | - | - | |
2026.03 | 80.55 | - | - | |
2026.01 | 79.9 | - | - | |
2026.01 | 79.8 | - | - | |
2026.03 | 79.63 | - | - | |
2026.03 | 79.53 | - | - | |
2026.02 | 79.49 | - | - | |
2026.01 | 79.2 | 20 | - | |
2026.01 | 79.2 | 20 | - | |
2026.02 | 79.2 | - | - | |
2026.02 | 79.16 | - | - | |
2026.01 | 78.8 | 20 | - | |
2026.01 | 78.8 | 20 | - | |
2026.01 | 78.8 | - | - | |
2026.01 | 78.8 | - | - | |
2026.02 | 78.64 | - | - | |
2026.03 | 78.4 | - | - | |
| 78.38 | - | - | ||
2026.03 | 77.74 | - | - | |
2026.03 | 77.74 | - | - | |
2026.03 | 77.53 | - | - | |
2026.03 | 77.28 | - | - | |
2026.03 | 76.15 | - | - | |
2026.03 | 76 | - | - | |
2026.01 | 75.9 | - | - | |
2026.01 | 75.8 | - | - | |
2026.01 | 75.8 | - | - | |
2026.01 | 75.8 | - | - | |
2026.03 | 75.74 | - | - | |
2026.03 | 75.74 | - | - | |
2026.03 | 75.08 | - | - | |
2026.03 | 74.51 | - | - | |
2026.03 | 74.51 | - | - | |
2026.01 | 74 | - | - | |
2026.01 | 74 | - | - | |
2026.01 | 73.4 | -10 | - | |
2026.01 | 73.4 | -10 | - | |
2026.03 | 73.23 | - | - | |
2026.03 | 73.18 | - | - | |
2026.03 | 73.13 | - | - | |
2026.03 | 73.08 | - | - | |
2026.03 | 72.82 | - | - | |
2026.01 | 72.2 | - | - | |
2026.01 | 72.2 | - | - | |
2026.03 | 72.01 | - | - | |
2026.01 | 70.7 | 0 | - | |
2026.01 | 70.6 | -20 | - | |
2026.01 | 70.2 | 20 | - | |
2026.01 | 70.2 | 20 | - | |
2026.01 | 69.4 | - | - | |
2026.01 | 69.4 | - | - | |
2026.01 | 68.9 | 30 | - | |
2026.01 | 68.9 | 30 | - | |
2026.01 | 68.1 | 40 | - | |
2026.01 | 68 | 30 | - | |
2026.01 | 64.9 | 10 | - | |
2026.01 | 64.9 | 10 | - | |
2026.01 | 64.7 | -20 | - | |
2026.01 | 64.7 | -20 | - | |
2026.01 | 62.7 | 0 | - | |
2026.01 | 62.7 | 0 | - | |
2026.01 | 62.6 | -10 | - | |
2026.01 | 62.6 | -10 | - | |
2026.01 | 62.5 | - | - | |
2026.01 | 62.5 | - | - | |
2026.01 | 61.1 | -10 | - | |
2026.01 | 61.1 | -10 | - | |
2026.01 | 60.8 | -30 | - | |
2026.01 | 60.8 | -30 | - | |
2026.01 | 59.9 | 10 | - | |
2026.01 | 59.9 | 20 | - | |
2026.01 | 58 | - | - | |
2026.01 | 57.9 | - | - | |
2026.01 | 55.4 | 40 | - | |
2026.01 | 55.1 | 10 | - | |
2026.01 | 52 | -30 | - | |
2026.01 | 52 | -30 | - | |
2026.01 | 52 | - | - | |
2026.01 | 52 | - | - | |
2026.01 | 48.5 | 50 | - | |
2026.01 | 48.5 | 50 | - | |
2026.01 | 48.1 | 10 | - | |
2026.01 | 48.1 | 10 | - | |
2026.03 | 47.51 | - | - | |
2026.03 | 46.21 | - | - | |
2026.03 | 45.02 | - | - | |
2026.03 | 44.36 | - | - | |
2026.03 | 43.58 | - | - | |
2026.03 | 43.57 | - | - | |
2026.03 | 43.43 | - | - |
Showing 100 of 110 rows