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

Multi-task Evaluation on Aggregate (HealthQA, ARC-C, PopQA, Squad1, ASQA)

62.8Average Score

AMATA 8B

34.09641.5484956.452May 17, 2026
Updated 15d ago

Evaluation Results

MethodLinks
2026.05
62.8
2026.05
60.1
2026.05
59.76
2026.05
59.29
2026.05
51.81
2026.05
49.17
2026.05
35.25
2026.05
35.2