Natural Language Inference on MultiMed-X ZU
0.68AccuracyMED-COREASONER
Evaluation Results
| Method | Links | |
|---|---|---|
| MED-COREASONERbackbone=GPT-5.12026.01 | 0.68 | |
| GPT-5.22026.01 | 0.66 | |
| GPT-4o2026.01 | 0.66 | |
| GPT-5.12026.01 | 0.64 | |
| Claude-3.5-haiku2026.01 | 0.62 |
| Method | Links | |
|---|---|---|
| MED-COREASONERbackbone=GPT-5.12026.01 | 0.68 | |
| GPT-5.22026.01 | 0.66 | |
| GPT-4o2026.01 | 0.66 | |
| GPT-5.12026.01 | 0.64 | |
| Claude-3.5-haiku2026.01 | 0.62 |