Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Pairwise classification on PMR-Real (Hard)
Loading...
0.72
Accuracy
MedGemma-27BSFT
0.3976
0.4813
0.565
0.6487
Jan 19, 2026
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
MedGemma-27BSFT
Method=UrgentSFT
2026.01
0.72
Qwen3-4BSFT
Method=UrgentSFT
2026.01
0.67
Qwen3-8BSFT
Method=UrgentSFT
2026.01
0.64
Reward-4Burgent
Method=UrgentReward
2026.01
0.63
Reward-8Burgent
Method=UrgentReward
2026.01
0.63
Reward-4Bbase
Type=Base
2026.01
0.61
Qwen3-8B
Size=8B
2026.01
0.6
MedGemma-27b
Size=27B
2026.01
0.6
Qwen3-32B
Size=32B
2026.01
0.58
Reward-8Bbase
Type=Base
2026.01
0.57
GPT-OSS
Size=20B
2026.01
0.56
Qwen3-4B
Size=4B
2026.01
0.51
Qwen3-32B-R
Size=32B, Reasoning=True
2026.01
0.41
Feedback
Search any
task
Search any
task