Skip to content

Benchmark

Arena ELO Text Factuality - Coding

Coding benchmarks compare models on programming tasks. Higher scores are better.

Models measured
155
Scores recorded
174
Sources
1
IQ weight
1.95

Score distribution

1,491.4
Mean
1,494.7
Median
38
Std dev
1,437
10th percentile
1,534.3
90th percentile
1,344.9
Min
1,344.91,567
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.95 for chat models, measured over 155 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

Showing 151–174 of 174 results.

Data credits: LMArena, CC BY 4.0 (licence)