Skip to content

Benchmark

EvalPerf Model Win Rate

Coding benchmarks compare models on programming tasks. Scores are percentages. Higher is better.

Models measured
25
Scores recorded
26
Sources
1
IQ weight
0.99

Score distribution

52.2%
Mean
54.5%
Median
29.9%
Std dev
15.2%
10th percentile
90.9%
90th percentile
0%
Min
0%100%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.99 for chat models, measured over 25 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

Data credits: EvalPlus Leaderboard and EvalPerf (evalplus.github.io), Apache-2.0; EvalPerf win-rate fractions converted to percentages (licence)