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

Multi-domain Evaluation on MMLU, GSM8K, HEval, BBH, MedQA

68Average Score

CODA

53.9657.60561.2564.895Jul 3, 2026
Updated 19d ago

Evaluation Results

MethodLinks
2026.07
68
2026.07
66.8
2026.07
66.7
2026.07
66.6
2026.07
66.4
2026.07
66.2
2026.07
66
2026.07
65.7
2026.07
65.5
2026.07
57.2
2026.07
56
2026.07
55.8
2026.07
55.7
2026.07
55.5
2026.07
55.4
2026.07
55.1
2026.07
54.7
2026.07
54.5