Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Medical Question Answering on HealthBench (All Set)
Loading...
58.56
Overall Score
GPT-5.4
54.6912
55.6956
56.7
57.7044
Mar 23, 2026
Overall Score
Accuracy
Completeness
Instruction Following
Context Awareness
Communication Quality
Updated 2mo ago
Evaluation Results
Method
Method
Links
Overall Score
Accuracy
Completeness
Instruction Following
Context Awareness
Communication Quality
GPT-5.4
2026.03
58.56
63.36
53.14
47.49
63.33
55.62
GPT-5.2
2026.03
55.59
63.17
50.1
51.93
50.27
44.7
Oph-Guid-Rag
2026.03
55.24
62.66
46.14
34.74
62.12
41.53
GPT-5.3
2026.03
54.84
56.9
45.74
56.72
53.17
47.17
Feedback
Search any
task
Search any
task