Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Pairwise classification on PMR-Real (Total)
Loading...
77
Accuracy
MedGemma-27BSFT
52.04
58.52
65
71.48
Jan 19, 2026
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
MedGemma-27BSFT
Method=UrgentSFT
2026.01
77
Qwen3-4BSFT
Method=UrgentSFT
2026.01
75
Reward-4Burgent
Method=UrgentReward
2026.01
75
Qwen3-8BSFT
Method=UrgentSFT
2026.01
74
Reward-8Burgent
Method=UrgentReward
2026.01
74
Qwen3-32B
Size=32B
2026.01
70
Reward-4Bbase
Type=Base
2026.01
70
Qwen3-8B
Size=8B
2026.01
68
MedGemma-27b
Size=27B
2026.01
68
Reward-8Bbase
Type=Base
2026.01
67
Qwen3-4B
Size=4B
2026.01
66
GPT-OSS
Size=20B
2026.01
63
Qwen3-32B-R
Size=32B, Reasoning=True
2026.01
53
Feedback
Search any
task
Search any
task