DataLearner logo

CodeLlama-70B-Python Benchmark Details

CodeLlama-70B-Python currently shows benchmark results led by MBPP (21 / 70, score 65.60), HumanEval (44 / 101, score 57.30).

Benchmark Results

CodeLlama-70B-Python

Benchmark Results

Thinking

Coding and Software Engineer

2 evaluations
Benchmark / mode
Score
Rank/total
MBPP
Standard Mode
65.60
21 / 70
HumanEval
Standard Mode
57.30
44 / 101
Compare with other models