Skip to content

Benchmark

Vals Vibe Code Bench 1-100

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

Models measured
24
Scores recorded
24
Sources
1
IQ weight
2.17

Score distribution

19.2%
Mean
18.8%
Median
7.1%
Std dev
9.2%
10th percentile
28.5%
90th percentile
6.7%
Min
6.7%34%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.17 for chat models, measured over 24 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard