Skip to content

Benchmark

Agentset Reranker Elo - arguana

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

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

Score distribution

1,421.5
Mean
1,472
Median
265.6
Std dev
1,106
10th percentile
1,783
90th percentile
1,080
Min
1,0801,783
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Rerank V4.0 Proarguana· Agentset1,783
2Rerank V3.5arguana· Agentset1,692
3Rerank V4.0 Fastarguana· Agentset1,472
4Jina Reranker v2 Base Multilingualarguana· Agentset1,396
5BGE Reranker v2 M3arguana· Agentset1,106
6Qwen3 Reranker 8Barguana· Agentset1,080