Reading Comprehension on OpenBookQA
96AccuracyLlama-3.3-70B-Instruct
Evaluation results
| Method | Links | |
|---|---|---|
| Llama-3.3-70B-InstructShots=52026.04 | 96 | |
| Qwen3.5-9BShots=52026.04 | 94.6 | |
| Qwen3-14BShots=52026.04 | 94 | |
| XekRung-8BShots=52026.04 | 93.8 | |
| Qwen3-8BShots=52026.04 | 91 | |
| SecGPT-14BShots=52026.04 | 89.8 | |
| GPT-3Shots=12023.03 | 58.8 | |
| OPT66BShots=12023.03 | 58 | |
| BloombergGPTShots=12023.03 | 51.6 | |
| BLOOM176BShots=12023.03 | 47.2 | |
| GPT-NeoXShots=12023.03 | 44.2 | |
| Llama-Primus-Reasoning-8BShots=52026.04 | 30.8 | |
| Llama-3.1-8B-InstructShots=52026.04 | 26.4 |