Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Medical Diagnosis on MediQ (test)
Loading...
74.67
Average Outcome Reward
O4-MINI
33.6732
44.3166
54.96
65.6034
Mar 12, 2026
Average Outcome Reward
Updated 1mo ago
Evaluation Results
Method
Method
Links
Average Outcome Reward
O4-MINI
Training Protocol=DIRE...
2026.03
74.67
AREW– AS ONLY
Training Protocol=PPO-...
2026.03
71.75
AREW– AS + BT
Training Protocol=PPO-...
2026.03
70.75
VANILLA
Training Protocol=PPO-...
2026.03
63.5
AREW– AS + BT
Training Protocol=PPO-...
2026.03
61.25
AREW– AS ONLY
Training Protocol=PPO-...
2026.03
57.25
VANILLA
Training Protocol=PPO-...
2026.03
50.5
QWEN-2.5-7B-INST.
Training Protocol=DIRE...
2026.03
39
LLAMA-3.1-8B-INST.
Training Protocol=DIRE...
2026.03
35.25
Feedback
Search any
task
Search any
task