Skip to content

Benchmark

Agentset Reranker Win Rate - arguana

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

Models measured
6
Scores recorded
6
Sources
1
IQ weight
No weight published

Score distribution

43.4%
Mean
47.4%
Median
18.5%
Std dev
36.9%
10th percentile
66.2%
90th percentile
10.4%
Min
10.4%66.2%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Rerank V4.0 Proarguana· Agentset66.2%
2Rerank V4.0 Fastarguana· Agentset62.2%
3Rerank V3.5arguana· Agentset47.4%
4Jina Reranker v2 Base Multilingualarguana· Agentset37.5%
5Qwen3 Reranker 8Barguana· Agentset36.9%
6BGE Reranker v2 M3arguana· Agentset10.4%