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

General Knowledge on MMLU (pass@1)

72.48pass@1

SPINE

17.006431.408245.8160.2118Nov 22, 2025Dec 5, 2025Dec 19, 2025Jan 2, 2026Jan 15, 2026Jan 29, 2026Feb 12, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2025.11
72.48
2025.11
71.74
2025.11
71.19
2025.11
69.36
2026.02
68.39
2025.11
65.39
2026.02
65.17
2026.02
64.85
2026.02
63.76
2026.02
63.47
2026.02
61.83
2026.02
58.94
2025.11
58.16
2026.02
57.12
2026.02
43.23
2026.02
41.78
2026.02
38.79
2026.02
26.29
2026.02
26.29
2026.02
19.37
2026.02
19.28
2026.02
19.14