Chinese Reasoning on OCNLI
74.4AccuracyQwen3.5-9B
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3.5-9BShots=52026.04 | 74.4 | |
| Llama-3.3-70B-InstructShots=52026.04 | 71.59 | |
| XekRung-8BShots=52026.04 | 69.96 | |
| Qwen3-14BShots=52026.04 | 69.72 | |
| Qwen3-8BShots=52026.04 | 68.81 | |
| SecGPT-14BShots=52026.04 | 67.66 | |
| Llama-3.1-8B-InstructShots=52026.04 | 43.81 | |
| Llama-Primus-Reasoning-8BShots=52026.04 | 30.6 | |
| Foundation-Sec-8B-ReasoningShots=52026.04 | 18.33 |