Clinical Question Answering on Medications
1.24CCorOpenthinker 32B
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Openthinker 32BParameters=32B, Evaluation Protocol=GPT-5.42025.07 | 1.24 | 1.25 | 1.24 | 1.83 | 67.33 | |
| MACEvaluation Protocol=GPT-5.42025.07 | 1.24 | 1.36 | 1.32 | 1.91 | 70.33 | |
| Deepseek-R1 32BParameters=32B, Evaluation Protocol=GPT-5.42025.07 | 1.21 | 1.12 | 1.17 | 1.77 | 67.33 | |
| Phi4 14BParameters=14B, Evaluation Protocol=GPT-5.42025.07 | 1.2 | 1.13 | 1.21 | 1.69 | 67 | |
| Qwen2.5 14BParameters=14B, Evaluation Protocol=GPT-5.42025.07 | 1.19 | 1.05 | 1.19 | 1.74 | 67.67 | |
| Qwen2.5 32BParameters=32B, Evaluation Protocol=GPT-5.42025.07 | 0 | 0 | 0 | 0.25 | 0 | |
| QWQ 32BParameters=32B, Evaluation Protocol=GPT-5.42025.07 | 0 | 0 | 0.01 | 0.26 | 0 |