Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Medical Agent Task Completion on MedAgentBench
Loading...
73.3
Accuracy
LLM-as-a-Verifier
64.772
66.986
69.2
71.414
Jul 6, 2026
Accuracy
Pass@1
Oracle Score
Updated 19d ago
Evaluation Results
Method
Method
Links
Accuracy
Pass@1
Oracle Score
LLM-as-a-Verifier
2026.07
73.3
-
-
Opus 4.8
Baseline Rank=#1
2026.07
70.2
-
-
G3.5 Flash
Baseline Rank=#2
2026.07
66.3
-
-
GPT-5.5
Baseline Rank=#3
2026.07
65.1
-
-
Candidate Pool
2026.07
-
70.2
75
Feedback
Search any
task
Search any
task