List your company

Medical Knowledge on HealthBench (Pass@1)

92.82Pass@1GPT-5.2-chat (teacher)
82.9485.50588.0790.635May 8, 2026

Evaluation results

MethodLinks
GPT-5.2-chat (teacher)2026.0592.82
ROPDThinking Mode=Thinking2026.0586.87
OVDThinking Mode=Thinking2026.0585.98
GADThinking Mode=Thinking2026.0585.7
T-JudgeThinking Mode=Thinking2026.0585.58
Qwen3-4B (student)Thinking Mode=Thinking2026.0585.3
ROPDThinking Mode=Non-Thinking2026.0584.92
T-JudgeThinking Mode=Non-Thinking2026.0584.52
OVDThinking Mode=Non-Thinking2026.0583.68
GADThinking Mode=Non-Thinking2026.0583.57
Qwen3-4B (student)Thinking Mode=Non-Thinking2026.0583.32