Skip to content

Benchmark

MBPP ++ base version

Coding benchmarks compare models on programming tasks. Scores are percentages.

Models measured
1
Scores recorded
1
Sources
1
IQ weight
No weight published

Score distribution

86%
Mean
86%
Median
0%
Std dev
86%
10th percentile
86%
90th percentile
86%
Min

Leaderboard

#ModelScore
1Llama 3.1 70B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim86%

Data credits: Data by LLM Stats