Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

General Knowledge on Knowledge Benchmarks (ARC-C, ARC-E, MMLU, GPQA) (test)

83.05ARC-C

Task Arithmetic

-3.32219.101541.52563.9485Jan 9, 2026
Updated 3d ago

Evaluation Results

MethodLinks
2026.01
83.0590.8363.6939.39-
2026.01
80.6889.7761.538.64-
2026.01
80.3489.7763.459.85-
2026.01
8089.5961.690-
2026.01
79.6689.2460.625.76-
2026.01
79.3289.2464.5943.18-
2026.01
77.2988.3659.6436.36-
2026.01
73.986.0755.7534.09-
2026.01
70.8583.9553.2547.51-
2026.01
64.7577.2552.5149.1-
2026.01
64.3173.3973.4644.85-
2026.01
63.5670.4361.8137.88-
2026.01
60.3467.0271.5140.15-
2026.01
60.3466.1957.0424.24-
2026.01
32.5433.8971.9338.64-
2026.01
21.3626.6322.9534.09-
2026.01
17.9713.9323.462.27-
2026.01
0022.950-