CodeLLaMA-34B Benchmark Details

CodeLLaMA-34B currently shows benchmark results led by MBPP pass@10 (2 / 13, score 76.20), HumanEval pass@100 (4 / 21, score 93), HumanEval pass@10 (5 / 18, score 76.80).

Benchmark Results

CodeLLaMA-34B

Benchmark Results

Coding and Software Engineer

2 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

55

34 / 70

Standard Mode

48.80

52 / 101

Other

4 evaluations

Benchmark / mode

Score

Rank/total

HumanEval pass@100

Standard Mode

93

4 / 21

Standard Mode

86.60

4 / 13

HumanEval pass@10

Standard Mode

76.80

5 / 18

Standard Mode

76.20

2 / 13

Compare with other models