Skip to content

Benchmark

Agentset Reranker Elo - DBPedia

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

1,477.2
Mean
1,491
Median
114.5
Std dev
1,346
10th percentile
1,644
90th percentile
1,326
Min
1,3261,644
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Qwen3 Reranker 8BDBPedia· Agentset1,644
2Rerank V4.0 FastDBPedia· Agentset1,580
3Rerank V4.0 ProDBPedia· Agentset1,491
4Rerank V3.5DBPedia· Agentset1,476
5BGE Reranker v2 M3DBPedia· Agentset1,346
6Jina Reranker v2 Base MultilingualDBPedia· Agentset1,326