Skip to content

Benchmark

BigCodeBench Instruct

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

Models measured
71
Scores recorded
71
Sources
1
IQ weight
1.82

Score distribution

36.9%
Mean
38.7%
Median
10.8%
Std dev
20.5%
10th percentile
48.2%
90th percentile
7%
Min
7%51.1%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.82 for chat models, measured over 71 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

Showing 51–71 of 71 results.