NLI on MultiMed-X KO
0.6733AccuracyMED-COREASONER
Evaluation Results
| Method | Links | |
|---|---|---|
| MED-COREASONERbackbone=GPT-5.12026.01 | 0.6733 | |
| GPT-5.22026.01 | 0.6467 | |
| GPT-5.12026.01 | 0.6267 | |
| GPT-4o2026.01 | 0.6133 | |
| Claude-3.5-haiku2026.01 | 0.6 |
| Method | Links | |
|---|---|---|
| MED-COREASONERbackbone=GPT-5.12026.01 | 0.6733 | |
| GPT-5.22026.01 | 0.6467 | |
| GPT-5.12026.01 | 0.6267 | |
| GPT-4o2026.01 | 0.6133 | |
| Claude-3.5-haiku2026.01 | 0.6 |