Skip to content

Benchmark

CAD-Eval

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

Models measured
14
Scores recorded
14
Sources
1
IQ weight
1.48

Score distribution

43.1%
Mean
48%
Median
18%
Std dev
16%
10th percentile
64%
90th percentile
12%
Min
12%74%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.48 for chat models, measured over 14 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: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)