Agentset Reranker Leaderboard — leaderboard
RAG reranker leaderboard comparing retrieval reranking models across six datasets using pairwise judgments and Elo ratings.
Metric: Elo. Source: github.com. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Zerank 2 | 1638 |
| 2 | Cohere Rerank 4 Pro | 1629 |
| 3 | Zerank 1 | 1573 |
| 4 | Voyage AI Rerank 2.5 | 1544 |
| 5 | Zerank 1 Small | 1539 |
| 6 | Voyage AI Rerank 2.5 Lite | 1520 |
| 7 | Cohere Rerank 4 Fast | 1510 |
| 8 | Qwen3 Reranker 8B | 1473 |
| 9 | Contextual AI Rerank v2 Instruct | 1469 |
| 10 | Cohere Rerank 3.5 | 1451 |
Interactive version: theaggregate.ai/benchmark?slug=agentset-reranker-leaderboard · How the rankings work · Data refreshed daily, snapshot 2026-07-22.