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

Factual Knowledge on MMLU (test)

47.9Accuracy

Alpaca-GPT4 + SelectIT

43.022444.288745.55546.8213Mar 13, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
47.937.163.15
2026.03
47.8137.183.2
2026.03
47.7836.471.23
2026.03
47.5137.062.88
2026.03
47.1435.69-0.94
2026.03
46.8736.03-
2026.03
46.8337.23.24
2026.03
46.7335.68-0.98
2026.03
46.4537.74.65
2026.03
46.1736.711.89
2026.03
45.236.170.39
2026.03
43.2135.18-2.34