Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Hallucination Suppression on HealthBench Hallu
Loading...
2.37
Refuted Rate
GPT-5.2-High
2.2356
3.1428
4.05
4.9572
Feb 6, 2026
Refuted Rate
Uncertain Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
Refuted Rate
Uncertain Rate
GPT-5.2-High
2026.02
2.37
2.78
Baichuan-M3-235B
Fact-Aware RL=true, Pa...
2026.02
2.45
2.07
Baichuan-M3
Fact-Aware RL=false
2026.02
4.68
3.64
Baichuan-M2-32B
Parameters=32B
2026.02
5.73
5.43
Feedback
Search any
task
Search any
task