Code Benchmarks
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
Code Benchmarks LCBv6 & MBPP+
32.8LCBv6 Score
19
Code Benchmarks HumanEval MBPP
72.29HumanEval
18
Code Benchmarks (HumanEval, MBPP)
30.1HumanEval Score
17
Code Benchmarks Aggregate
37.5Score
12
Code Benchmarks Total
26.4Avg@8
4
Code Benchmarks HumanEval, HumanEval+, MBPP, MBPP+ (test)
55.5HumanEval Score
3
Code Benchmarks (test)
34.1HumanEval
3