List your company

ResearchFormerly WizWand

Programming

Benchmarks

DatasetSOTA methodMetricTrendResultsLast updated

LiveCodeBench V3 V4 (test)

61.4Accuracy

42

May 6, 2026

HumanEval (test)

79.5ACC1

11

Feb 26, 2026

ChatGPT o1-mini

79.5ACC1

3

Feb 26, 2026