Skip to content

Benchmark

BuiltBench(eng) - Reranking

Rerank benchmarks measure how well models put the most relevant search results first. Scores are percentages.

Models measured
16
Scores recorded
16
Sources
1
IQ weight
0.67

Score distribution

65.4%
Mean
65.5%
Median
3.7%
Std dev
62.4%
10th percentile
70.3%
90th percentile
56.6%
Min
56.6%73.3%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.67 for embedding models, measured over 16 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard