Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Deep Research on HealthBench

59.5Score

GPT-5 + Search

-15.93.67523.2542.825Nov 24, 2025
Updated 16d ago

Evaluation Results

MethodLinks
2025.11
59.5
2025.11
53.8
2025.11
52.8
2025.11
46.2
2025.11
39.4
2025.11
38.1
2025.11
38
2025.11
36.5
2025.11
33.7
2025.11
32
2025.11
31.1
2025.11
24.5
2025.11
16.5
2025.11
11.1
2025.11
5.9
2025.11
-0.1
2025.11
-13