DecisionRAG MD2D297 Context - R@5: leaderboard
DecisionRAG v1 uses Jev (typesafe/jev-1.13), dense retrieval with Qwen3-Embedding-8B, BGE (bge-reranker-v2-m3), a Qwen3 8B reranker, and GPT 5 with low reasoning. Evaluation populations are MD2D with 4201 validation turns, CQA with 271 evidence-labeled development questions, MTRAG with 188 labeled IBM Cloud turns, and NQ with 500 seeded DAPR test questions. Main MTRAG gold labels are expanded using GPT 5 to judge the pooled top 5 documents; comparisons using the original official labels remain separate. Trained judges use Qwen3 Base at 1.7B, 4B, and 8B; their results are distinct from backbone language-model scores. All source-qualified harnesses and training variants remain separate. This uses 297 turns from 50 training dialogues, six-turn input, title-only descriptions, and 10 new pages, without help-center routing or choice. It is not comparable to main validation. Metric: Accuracy (%).
Metric: Accuracy (%). Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | DecisionRAG Jev Sharedcontext Ownnotepad | 69.7 | |
| 2 | DecisionRAG Jev Separatecontext Ownnotepad | 61.3 | |
| 3 | DecisionRAG Jev Separatecontext Nonenotepad | 54.5 |
Interactive version: theaggregate.ai/benchmark?slug=decisionrag-md2d297-context-r-5 · How It Works · Data refreshed daily, snapshot 2026-10-28.