Skip to content

Benchmark

Vals LiveCodeBench

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

Models measured
127
Scores recorded
134
Sources
1
IQ weight
2.89

Score distribution

71.5%
Mean
80.5%
Median
18.2%
Std dev
41.9%
10th percentile
87.5%
90th percentile
9.9%
Min
9.9%90.5%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.89 for chat models, measured over 127 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

Showing 101–134 of 134 results.