Skip to content

Benchmark

LiveBench code_generation

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

Models measured
51
Scores recorded
51
Sources
1
IQ weight
2.19

Score distribution

76.4%
Mean
76.1%
Median
5.6%
Std dev
69%
10th percentile
81.7%
90th percentile
63.4%
Min
63.4%93%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.19 for chat models, measured over 51 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
51Grok Build 0.1· LiveBench data63.4%

Showing 51–51 of 51 results.