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

Coding on HumanEval, MBPP

50.2HumanEval Score

D3

10.045620.470330.89541.3197Apr 12, 2026Apr 19, 2026Apr 27, 2026May 5, 2026May 13, 2026May 21, 2026May 29, 2026
Updated 1d ago

Evaluation Results

MethodLinks
2026.05
50.254.649.6
2026.05
46.551.246.5
2026.05
45.850.546.2
2026.05
44.249.844.9
2026.05
38.442.134.9
2026.04
20.7322.2-
2026.04
20.7324.8-
2026.04
20.6224.2-
2026.04
20.1223.2-
2026.04
20.1224.4-
2026.04
20.1222.4-
2026.04
19.5124.8-
2026.04
19.5123.4-
2026.04
19.5123.2-
2026.04
18.924.2-
2026.04
18.922.4-
2026.04
18.922.6-
2026.04
18.2923.2-
2026.04
18.2621.8-
2026.04
17.6826.2-
2026.04
17.6823.6-
2026.04
17.6822.4-
2026.04
17.6821.2-
2026.04
17.6824.8-
2026.04
17.6824-
2026.04
17.6825.4-
2026.04
17.0721.8-
2026.04
17.0722.2-
2026.04
17.0721.6-
2026.04
17.0723-
2026.04
17.0724.4-
2026.04
15.8526.2-
2026.04
15.2422.8-
2026.04
15.2422.2-
2026.04
11.5915.2-