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

Knowledge Preservation on Knowledge Datasets (ARC-C, ARC-E, MMLU, GPQA)

64.75ARC-C

Reasoning

-2.5914.892532.37549.8575Jan 9, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
64.7577.2552.5149.164.89
2026.01
64.3173.3972.7343.1859.33
2026.01
63.5670.4362.1435.6144.63
2026.01
60.9165.7871.7239.3950.85
2026.01
60.3466.1957.3428.7837.82
2026.01
32.5433.6971.9338.6444.14
2026.01
21.3626.6323.0829.5513.46
2026.01
17.9713.9325.953.037.31
2026.01
0022.9503.4