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

Zero-shot Reasoning on Reasoning Benchmarks Average

75.33Average Accuracy

FP16

30.578842.196953.81565.4331Jun 2, 2026Jun 4, 2026Jun 7, 2026Jun 10, 2026Jun 12, 2026Jun 15, 2026Jun 18, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
75.33
2026.06
72.6
2026.06
72.41
2026.06
71.39
2026.06
71.12
2026.06
71
2026.06
70.91
2026.06
70.9
2026.06
69.48
2026.06
68.58
2026.06
67.89
2026.06
67.81
2026.06
65.93
2026.06
65.35
2026.06
65
2026.06
64.85
2026.06
64.44
2026.06
63.48
2026.06
62.73
2026.06
62.42
2026.06
62.06
2026.06
61.06
2026.06
60.76
2026.06
60.61
2026.06
60.22
2026.06
60.14
2026.06
53.5
2026.06
53.3
2026.06
48
2026.06
47.6
2026.06
40.8
2026.06
40.5
2026.06
34
2026.06
32.3