HumanEval-X
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
HumanEval-X C++
94.5Compilation Success Rate
13
HumanEval-X v1 (test)
48.2Pass@1
13
HumanEval-X (test)
87.19CA@1 (C++ to Java)
11
HumanEval-X JavaScript (test)
0.625AUROC
6
HumanEval-X Go (test)
67.3AUROC
6
HumanEval-X Go
98.2Quality (%)
4
HumanEval-X Java
100Quality (%)
4
HumanEval-X Javascript
98.2Quality (%)
4
HumanEval-X CPP
100Quality
4
HumanEval-X 1.0 (test)
54.22Pass@1
4
HumanEval-X 1.0 (test)
38.97Pass@1
4
HumanEval-X 1.0 (test)
33.38Pass@1
4
HumanEval-X 1.0 (test)
56.55Pass@1
4
HumanEval-X 1.0 (test)
46.87Pass@1
4
HumanEval-X 1.0 (test)
34Pass@1
4
HumanEval-X 1.0 (test)
49.67Pass@1
4
HumanEval-X 1.0 (test)
75.03Pass@1
4
HumanEval-X 1.0 (test)
54.51Pass@1
4
HumanEval-X 1.0 (test)
71.68Pass@1
4
HumanEval-X 1.0 (test)
62.79Pass@1
4
HumanEval-X 1.0 (test)
28.87Pass@1
4
HumanEval-X 1.0 (test)
41.98Pass@1
4
HumanEval-X 1.0 (test)
35.94Pass@1
4
HumanEval-X
89.8Pass@1 (Python)
4
HumanEval-X Go
97.1Quality Score
2