State Updating on AMA-Bench (SU)
58.73Success Metric
QWEN3.5-397B-A17B
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.06 | 58.73 | |
2026.06 | 53.94 | |
2026.06 | 49.77 | |
2026.06 | 49.3 | |
2026.06 | 48.38 | |
2026.06 | 48.38 | |
2026.06 | 47.14 | |
2026.06 | 47.14 | |
2026.06 | 46.99 | |
2026.06 | 43.74 | |
2026.06 | 42.81 | |
2026.06 | 34.93 | |
2026.06 | 31.53 | |
2026.06 | 30.91 | |
2026.06 | 30.14 | |
2026.06 | 29.68 | |
2026.06 | 28.44 | |
2026.06 | 27.67 | |
2026.06 | 24.88 | |
2026.06 | 24.42 |