Benchmark
Agentset Reranker Win Rate - PG
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
- 44.3%
- Mean
- 47.6%
- Median
- 12.4%
- Std dev
- 29.3%
- 10th percentile
- 61.3%
- 90th percentile
- 28.9%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Qwen3 Reranker 8BPG· Agentset | 61.3% |
| 2 | Rerank V4.0 ProPG· Agentset | 56.9% |
| 3 | Rerank V3.5PG· Agentset | 47.6% |
| 4 | Rerank V4.0 FastPG· Agentset | 41.6% |
| 5 | BGE Reranker v2 M3PG· Agentset | 29.3% |
| 6 | Jina Reranker v2 Base MultilingualPG· Agentset | 28.9% |