CodeLLaMA-Python-13B Benchmark Details

CodeLLaMA-Python-13B currently shows benchmark results led by HumanEval (4 / 140, score 94.10), MBPP (4 / 96, score 87.60).

Benchmark Results

CodeLLaMA-Python-13B

Benchmark Results

Coding and Software Engineer

6 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

94.10

4 / 140

Standard Mode

77.40

44 / 140

Standard Mode

43.30

92 / 140

Standard Mode

87.60

4 / 96

Standard Mode

74

31 / 96

Standard Mode

49

69 / 96

Compare with other models