EnterpriseRAG Bench - Recall: leaderboard
The "Recall" subtask of EnterpriseRAG Bench. Onyx's enterprise retrieval-augmented generation benchmark — question answering over realistic company document corpora, scoring answer correctness, completeness, recall and resistance to plausible-but-irrelevant extra documents.
Metric: Score (%). Source: huggingface.co. 34 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Mixedbread (+ Opus 5) | 94.28 | |
| 2 | Flexor.ai (+ GPT‑6.1 Sol) | 93.62 | |
| 3 | CDL (Causal Dynamics Lab) | 93.13 | |
| 4 | Neurond AI (neurond.com) | 92.3 | |
| 5 | PERSONA AI (personaai.co.kr) | 88.2 | |
| 6 | Prism (aurait.ai) | 87.81 | |
| 7 | Troml | 86.55 | |
| 8 | Skyller AI | 86.5 | |
| 9 | ZNV AgentCube | 86.1 | |
| 10 | metor.com | 85.53 |
Interactive version: theaggregate.ai/benchmark?slug=enterpriserag-bench-recall · How It Works · Data refreshed daily, snapshot 2026-10-20.