CodeLLaMA-Python-34B Benchmark Details

CodeLLaMA-Python-34B currently shows benchmark results led by HumanEval pass@100 (1 / 21, score 94.70), HumanEval pass@10 (1 / 18, score 82.80), MBPP pass@100 (1 / 13, score 88.20).

Benchmark Results

CodeLLaMA-Python-34B

Benchmark Results

Coding and Software Engineer

2 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

56.20

32 / 70

Standard Mode

53.70

46 / 101

Other

4 evaluations

Benchmark / mode

Score

Rank/total

HumanEval pass@100

Standard Mode

94.70

1 / 21

Standard Mode

88.20

1 / 13

HumanEval pass@10

Standard Mode

82.80

1 / 18

Standard Mode

76.40

1 / 13

Compare with other models