Medical Diagnosis on MediQ (test)
74.67Average Outcome RewardO4-MINI
Evaluation Results
| Method | Links | |
|---|---|---|
| O4-MINITraining Protocol=DIRECT INFERENCE2026.03 | 74.67 | |
| AREW– AS ONLYTraining Protocol=PPO-TRAINED, Backbone=LLAMA-3.1-8B-INST.2026.03 | 71.75 | |
| AREW– AS + BTTraining Protocol=PPO-TRAINED, Backbone=LLAMA-3.1-8B-INST.2026.03 | 70.75 | |
| VANILLATraining Protocol=PPO-TRAINED, Backbone=LLAMA-3.1-8B-INST.2026.03 | 63.5 | |
| AREW– AS + BTTraining Protocol=PPO-TRAINED, Backbone=QWEN-2.5-7B-INST.2026.03 | 61.25 | |
| AREW– AS ONLYTraining Protocol=PPO-TRAINED, Backbone=QWEN-2.5-7B-INST.2026.03 | 57.25 | |
| VANILLATraining Protocol=PPO-TRAINED, Backbone=QWEN-2.5-7B-INST.2026.03 | 50.5 | |
| QWEN-2.5-7B-INST.Training Protocol=DIRECT INFERENCE2026.03 | 39 | |
| LLAMA-3.1-8B-INST.Training Protocol=DIRECT INFERENCE2026.03 | 35.25 |