Drug-drug interaction reasoning on CoEval custom Drug-drug interaction reasoning vertical
77CoEval Ensemble Score (%)gpt-4o-mini
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| gpt-4o-mini2026.06 | 77 | 73.9 | |
| gpt-3.5-turbo2026.06 | 68.2 | 64.6 | |
| llama-3.2-3b2026.06 | 49.7 | 45.9 |
Loading the SOTA2 catalog…