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

Chain-of-Thought Reasoning on GPQA Diamond

67.93Accuracy

Vanilla

17.375630.500343.62556.7497Jun 1, 2026
Updated 1d ago

Evaluation Results

MethodLinks
2026.06
67.935,988-
2026.06
67.685,7204.5
2026.06
64.98,9804.9
2026.06
64.659,442-
2026.06
64.659,0823.8
2026.06
63.148,9685
2026.06
625,9420.8
2026.06
61.995,9021.4
2026.06
40.48,1915.2
2026.06
38.388,637-
2026.06
35.738,2274.8
2026.06
19.328,3423.4