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