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

Medical Agent Task Execution on MedAgentBench

79.3Success Rate

Claude-4-Sonnet

11.59629.17346.7564.327Mar 6, 2026Mar 7, 2026Mar 8, 2026Mar 9, 2026Mar 10, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
79.3---
2026.03
74.8---
2026.03
71.3310069.3373.33
2026.03
67.3---
2026.03
65.1---
2026.03
64.3---
2026.03
61.2---
2026.03
60.899059.1162.66
2026.03
60.3394.3366.6654
2026.03
5899.3354.6661.33
2026.03
589556.6659.33
2026.03
57.3---
2026.03
56.6---
2026.03
5175.6641.3360.66
2026.03
50.2---
2026.03
47.6610030.6664.66
2026.03
45.5581.4444.2246.89
2026.03
38.4---
2026.03
30.4492.113228.88
2026.03
2489.3335.3312.66
2026.03
20.665021.3320
2026.03
19.6687309.33
2026.03
17.8---
2026.03
14.2---