Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Medical Diagnosis on MedEinst Robust 1.0

24.21Robust Accuracy

ECR-Agent (Qwen3-32B)

0.26926.484612.718.9154Jan 10, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.01
24.2133.75
2026.01
15.7851.87
2026.01
12.4647.12
2026.01
12.3642.98
2026.01
11.8643.46
2026.01
11.6853.88
2026.01
11.443.32
2026.01
11.3246.12
2026.01
11.2854.19
2026.01
11.2547.63
2026.01
11.1444.88
2026.01
10.9760.9
2026.01
10.3440.34
2026.01
8.1141.69
2026.01
7.1866.1
2026.01
6.1754.2
2026.01
3.236.74
2026.01
1.1944