Long-form QA on MultiMed-X ZU
4.42Overall ScoreMED-COREASONER
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| MED-COREASONERbackbone=GPT-5.12026.01 | 4.42 | 4.71 | 4.77 | 4.73 | 4.31 | 91.5 | |
| GPT-5.22026.01 | 4.21 | 4.28 | 4.44 | 4.715 | 4.195 | 86 | |
| GPT-5.12026.01 | 4.16 | 4.23 | 4.445 | 4.695 | 4.145 | 85 | |
| GPT-4o2026.01 | 3.78 | 3.805 | 3.875 | 4.605 | 3.885 | 72.5 | |
| Claude-3.5-haiku2026.01 | 3.67 | 3.705 | 3.865 | 4.505 | 3.685 | 64.5 |