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

Medical Domain Question Answering on HealthBench In-domain, Seen

22.97Score

EvoRubrics

5.2389.841514.44519.0485Jun 22, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
22.970.4227
2026.06
20.80.3664
2026.06
20.470.3833
2026.06
20.230.3774
2026.06
18.520.3427
2026.06
18.040.3303
2026.06
17.170.3207
2026.06
15.820.2775
2026.06
14.40.2592
2026.06
13.040.2375
2026.06
12.620.2248
2026.06
8.850.1889
2026.06
8.240.1423
2026.06
5.920.0804