English Knowledge on GPQA
51.52AccuracyLlama-3.3-70B-Instruct
Evaluation results
| Method | Links | |
|---|---|---|
| Llama-3.3-70B-InstructShots=52026.04 | 51.52 | |
| Qwen3-14BShots=52026.04 | 48.48 | |
| Qwen3.5-9BShots=52026.04 | 45.96 | |
| XekRung-8BShots=52026.04 | 43.43 | |
| Qwen3-8BShots=52026.04 | 41.92 | |
| Foundation-Sec-8B-ReasoningShots=52026.04 | 31.7 | |
| Llama-3.1-8B-InstructShots=52026.04 | 30.4 | |
| SecGPT-14BShots=52026.04 | 13.13 |