Multiple-choice Question Answering on KNIGHT Biology L1
97.4AccuracyHuman
Evaluation results
| Method | Links | |
|---|---|---|
| Humann=2002026.02 | 97.4 | |
| GPT-4o2026.02 | 95.98 | |
| Mistral Large2026.02 | 95.18 | |
| Claude 3 Haiku2026.02 | 95.05 | |
| Llama3-70B-InstructSize=70B, Type=Instruct2026.02 | 94.12 | |
| Qwen1.5 (1.8B)Size=1.8B2026.02 | 79.88 | |
| Gemma (2B)Size=2B2026.02 | 45.51 |