Long-query Safety on Long-query Safety English
91.06AccuracyQwen3-Max
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3-Max2026.07 | 91.06 | |
| Qwen3.5-397B2026.07 | 90.18 | |
| Oyster-II2026.07 | 89.18 | |
| Oyster-I2026.07 | 85.94 | |
| Qwen3-14B2026.07 | 57.13 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| Qwen3-Max2026.07 | 91.06 | |
| Qwen3.5-397B2026.07 | 90.18 | |
| Oyster-II2026.07 | 89.18 | |
| Oyster-I2026.07 | 85.94 | |
| Qwen3-14B2026.07 | 57.13 |