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

Code Generation on FullStackBench

72.3Pass@1

Claude-Opus-4.5

23.52436.18748.8561.513Dec 19, 2025Jan 2, 2026Jan 17, 2026Feb 1, 2026Feb 15, 2026Mar 2, 2026Mar 17, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
72.3
2026.03
71.4
2026.03
70.2
2026.03
69.7
2026.03
68.3
2026.03
66.4
2026.03
64.9
2026.03
64.9
2025.12
64.1
2026.03
63.5
2026.03
62.7
2025.12
62.5
2025.12
61.8
2025.12
61
2026.03
60.9
2025.12
60.7
2026.03
59.5
2025.12
58.89
2026.03
58.8
2026.03
57.4
2025.12
56.88
2025.12
56.37
2026.03
55.8
2025.12
55.28
2026.03
54.8
2025.12
53.35
2026.03
53.1
2026.03
52.9
2025.12
52.52
2025.12
51.27
2026.03
49.4
2026.03
48.6
2025.12
48.19
2025.12
47.95
2026.03
46.6
2025.12
42.68
2026.03
42.2
2025.12
41.08
2025.12
40.16
2026.03
39.7
2026.03
38.6
2026.03
32.3
2025.12
27.56
2025.12
27
2025.12
25.4