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

Code Generation on HumanEval (Acceptance Length and Speedup)

7.07Average Acceptance Length

BlockPilot

2.30683.54344.786.0166May 19, 2026May 27, 2026Jun 4, 2026Jun 12, 2026Jun 20, 2026Jun 28, 2026Jul 6, 2026
Updated 18d ago

Evaluation Results

MethodLinks
2026.06
7.075.21-
2026.06
6.774.46-
2026.06
6.764.98-
2026.06
6.514.28-
2026.05
6.474.68-
2026.06
6.454.74-
2026.06
6.324.66-
2026.06
6.34.65-
2026.06
5.874.32-
2026.06
5.684.19-
2026.07
5.64--
2026.05
5.554.26-
2026.07
5.52--
2026.07
5.43--
2026.07
5.38--
2026.07
5.37--
2026.06
5.193.82-
2026.06
5.113.77-
2026.07
4.95--
2026.06
4.843.19-
2026.07
4.74--
2026.07
4.64--
2026.07
4.59--
2026.06
4.583.37-
2026.06
4.413.26-
2026.07
4.33--
2026.07
4.16--
2026.07
4.14--
2026.06
3.892.56-
2026.06
3.762.76-
2026.05
3.742.52-
2026.06
3.332.45-
2026.06
3.222.12-
2026.06
3.171.89-
2026.06
3.112.29-
2026.06
3.051.84-
2026.06
3.051.75-
2026.06
3.052.25-
2026.06
3.011.74-
2026.05
2.952.52-
2026.05
2.492.09-
2026.06
-6.059.07
2026.06
-6.359.39