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

Code Generation on TACO Verified

96.3During-task Accuracy

Cloud LLM Cluster

40.34854.87469.483.926Jan 29, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
96.396.3-
2026.01
84.872.814.1
2026.01
82.266.619
2026.01
76.960.221.7
2026.01
75.861.219.2
2026.01
74.462.316.2
2026.01
71.658.917.7
2026.01
70.454.223
2026.01
69.856.718.7
2026.01
69.758.615.9
2026.01
66.854.817.9
2026.01
66.754.618.1
2026.01
65.848.526.3
2026.01
61.643.129.1
2026.01
60.848.919.6
2026.01
57.439.531.2
2026.01
56.54422.1
2026.01
55.238.230.8
2026.01
51.834.633.2
2026.01
51.137.826
2026.01
50.937.626.1
2026.01
48.134.228.9
2026.01
46.633.129
2026.01
442445.5
2026.01
442445.5
2026.01
43.724.244.6
2026.01
42.729.930
2026.01
42.729.930
2026.01
42.530.129.2