CodeLLaMA-Python-7B Benchmark Details

CodeLLaMA-Python-7B currently shows benchmark results led by HumanEval (13 / 140, score 90.60), MBPP (12 / 96, score 84.80).

Benchmark Results

CodeLLaMA-Python-7B

Benchmark Results

Coding and Software Engineer

6 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

90.60

13 / 140

Standard Mode

70.30

56 / 140

Standard Mode

38.40

100 / 140

Standard Mode

84.80

12 / 96

Standard Mode

70.30

35 / 96

Standard Mode

47.60

73 / 96

Compare with other models