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

General Reasoning on LiveBench

53.47Accuracy

PerSyn

7.741219.613131.48543.3569Oct 7, 2025Nov 16, 2025Dec 26, 2025Feb 4, 2026Mar 16, 2026Apr 25, 2026Jun 4, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2025.10
53.47
2025.10
52.06
2025.10
51.9
2025.10
50.59
2025.10
50
2025.10
49.08
2025.10
48.85
2025.10
47.5
2025.10
47.5
2025.10
47.33
2025.10
46.9
2025.10
46.34
2025.10
46.2
2025.10
46.2
2025.10
46.2
2025.10
46.2
2025.10
46.15
2025.10
45.6
2025.10
45
2025.10
45
2025.10
44.26
2025.10
43.02
2025.10
42.5
2025.10
41.9
2025.10
41.9
2025.10
39.4
2025.10
38.8
2025.10
38.1
2025.10
38.1
2025.10
37.84
2025.10
37.5
2025.10
37.5
2025.10
37.13
2025.10
36.9
2025.10
36.63
2025.10
36.09
2025.10
35.86
2025.10
35.42
2025.10
34.63
2025.10
33.8
2025.10
33.49
2025.10
33.25
2025.10
33.1
2025.10
32.87
2025.10
31.2
2025.10
30.6
2025.10
30.6
2025.10
29.4
2026.06
28.6
2025.10
28.1
2026.06
27.8
2026.06
25.8
2026.06
25.3
2025.10
15.6
2026.06
9.5