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

Code Generation on HumanEval (Speed, Latency, and Resource Usage)

89.02Accuracy

MetaGPT

13.599233.179652.7672.3404Sep 27, 2025Oct 24, 2025Nov 21, 2025Dec 19, 2025Jan 16, 2026Feb 13, 2026Mar 13, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
89.02---
2026.02
86.7---
2026.03
85---
2026.03
85---
2026.02
84.8---
2026.03
84.76---
2026.03
83.5---
2026.02
82.9---
2026.03
82.5---
2026.03
82.32---
2026.03
81.3---
2026.03
80.49---
2026.03
71.85---
2026.02
68.9---
2026.03
67.07---
2025.09
64.0211.7487.6419.14
2026.03
62.2---
2025.09
60.973.03338.2119.79
2026.02
59.8---
2025.09
58.534.77214.519.16
2025.09
56.712.62393.4719.06
2026.02
47.6---
2026.03
44.5---
2026.03
44.5---
2026.03
41.5---
2026.03
40.2---
2026.03
40.2---
2026.03
39.6---
2026.03
37.8---
2026.03
37.8---
2026.03
37.8---
2026.03
37.8---
2026.03
35.3---
2026.03
32.9---
2026.03
32.3---
2026.03
32.3---
2026.03
31.1---
2026.03
27.4---
2026.02
16.5---