Clinical Reasoning on CoEval custom Clinical reasoning vertical
87.3CoEval Ensemble Scoregpt-3.5-turbo
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| gpt-3.5-turbo2026.06 | 87.3 | 84.9 | |
| gpt-4o-mini2026.06 | 86.4 | 84 | |
| llama-3.2-3b2026.06 | 81.4 | 78.4 |
Loading the SOTA2 catalog…
| Method | Links | ||
|---|---|---|---|
| gpt-3.5-turbo2026.06 | 87.3 | 84.9 | |
| gpt-4o-mini2026.06 | 86.4 | 84 | |
| llama-3.2-3b2026.06 | 81.4 | 78.4 |