| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MedXpertQA text | o1 | Accuracy48.9 | 12 | 3d ago | |
| MMLU clinical topics | o1 | Accuracy91.6 | 12 | 3d ago | |
| PMC-MI-Bench | M3LLM-8B | BLEU@413 | 10 | 3d ago | |
| Personalized Text-only Question Answering 400 text questions 1.0 (test) | GPT-4V + Prompt | Accuracy98.7 | 9 | 3d ago | |
| MuSiQue | PixSearch | EM11.5 | 4 | 3d ago | |
| NQ | PixSearch | EM30.9 | 4 | 3d ago |