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

General Language Modeling on MMLU, ARC-Challenge, and CommonsenseQA Aggregate

64.77Average Score

RAISE

37.272444.411251.5558.6888Apr 9, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.04
64.7769.83
2025.04
64.4246.59
2025.04
64.2234.04
2025.04
64.1932.06
2025.04
64.1328.37
2025.04
63.9415.53
2025.04
63.70
2025.04
62.16-100
2025.04
55.4770.35
2025.04
54.7325.06
2025.04
54.320
2025.04
54.2-7.33
2025.04
54.05-16.44
2025.04
53.13-72.14
2025.04
52.67-100
2025.04
51.08-196.75
2025.04
40.2485.14
2025.04
40.0869.55
2025.04
39.447.01
2025.04
39.360
2025.04
39.2-15.77
2025.04
38.88-47.39
2025.04
38.69-65.79
2025.04
38.33-100