Skip to content

Benchmark

HREF Multi-document Synthesis

Instruction following benchmarks measure how closely models follow instructions. Scores are percentages.

Models measured
14
Scores recorded
14
Sources
1
IQ weight
0.95

Score distribution

28.7%
Mean
26.3%
Median
19.1%
Std dev
4.9%
10th percentile
60%
90th percentile
4.4%
Min
4.4%60.3%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.95 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