Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Pairwise classification on PMR-Synth (Hard)
Loading...
63
Accuracy
MedGemma-27b
37
43.75
50.5
57.25
Jan 19, 2026
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
MedGemma-27b
Size=27B
2026.01
63
Reward-8Burgent
Method=UrgentReward
2026.01
62
Qwen3-32BSFT
Method=UrgentSFT
2026.01
60
MedGemma-27BSFT
Method=UrgentSFT
2026.01
60
Reward-4Burgent
Method=UrgentReward
2026.01
56
Qwen3-8B
Size=8B
2026.01
55
Reward-8Bbase
Type=Base
2026.01
54
Reward-4Bbase
Type=Base
2026.01
53
Qwen3-8BSFT
Method=UrgentSFT
2026.01
52
Qwen3-32B
Size=32B
2026.01
51
Qwen3-4B
Size=4B
2026.01
50
GPT-OSS
Size=120B
2026.01
50
Qwen3-4BSFT
Method=UrgentSFT
2026.01
50
Qwen3-32B-R
Size=32B, Reasoning=True
2026.01
38
Feedback
Search any
task
Search any
task