CodeLLaMA-Instruct-7B Benchmark Details

CodeLLaMA-Instruct-7B currently shows benchmark results led by HumanEval pass@10 (10 / 18, score 64.30), HumanEval pass@100 (14 / 21, score 88.10), HumanEval (72 / 101, score 34.80).

Benchmark Results

CodeLLaMA-Instruct-7B

Benchmark Results

Coding and Software Engineer

2 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

44.40

55 / 70

Standard Mode

34.80

72 / 101

Other

4 evaluations

Benchmark / mode

Score

Rank/total

HumanEval pass@100

Standard Mode

88.10

14 / 21

Standard Mode

76.80

11 / 13

Standard Mode

65.40

10 / 13

HumanEval pass@10

Standard Mode

64.30

10 / 18

Compare with other models