Benchmark
Agentset Reranker Recall@10 - 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
- 83.7%
- Mean
- 88%
- Median
- 5.9%
- Std dev
- 78%
- 10th percentile
- 92%
- 90th percentile
- 76%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Rerank V4.0 Proarguana· Agentset | 92% |
| 2 | Qwen3 Reranker 8Barguana· Agentset | 88% |
| 3 | Rerank V4.0 Fastarguana· Agentset | 88% |
| 4 | Rerank V3.5arguana· Agentset | 80% |
| 5 | BGE Reranker v2 M3arguana· Agentset | 78% |
| 6 | Jina Reranker v2 Base Multilingualarguana· Agentset | 76% |