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

Code Generation on LiveCodeBench v6 (test) (Avg@4)

21.1Avg@4

AIPO

5.6049.62713.6517.673May 8, 2026
Updated 22d ago

Evaluation Results

MethodLinks
2026.05
21.1
2026.05
19.2
2026.05
19.2
2026.05
18.4
2026.05
18.1
2026.05
18.1
2026.05
17.3
2026.05
17
2026.05
16.4
2026.05
16.3
2026.05
15.9
2026.05
15.7
2026.05
12.4
2026.05
10.8
2026.05
10.1
2026.05
9.6
2026.05
8.7
2026.05
8
2026.05
7.5
2026.05
6.2