Skip to content

Benchmark

Vals Code Migration v1.1

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

Models measured
29
Scores recorded
29
Sources
1
IQ weight
1.96

Score distribution

49.9%
Mean
51.6%
Median
22%
Std dev
20.9%
10th percentile
80.6%
90th percentile
8.8%
Min
8.8%86.9%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.96 for chat models, measured over 29 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard