CodeLLaMA-Instruct-34B Benchmark Details

CodeLLaMA-Instruct-34B currently shows benchmark results led by HumanEval pass@100 (3 / 21, score 93.50), HumanEval pass@10 (4 / 18, score 77.20), MBPP pass@10 (3 / 13, score 74.60).

Benchmark Results

CodeLLaMA-Instruct-34B

Benchmark Results

Coding and Software Engineer

2 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

57

31 / 70

Standard Mode

41.50

59 / 101

Other

4 evaluations

Benchmark / mode

Score

Rank/total

HumanEval pass@100

Standard Mode

93.50

3 / 21

Standard Mode

85.40

5 / 13

HumanEval pass@10

Standard Mode

77.20

4 / 18

Standard Mode

74.60

3 / 13

Compare with other models