DecisionRAG Generative Control CQA - Hit@1: 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 is a fixed-hierarchy and budget comparison. NQ control-run observations differ from the main population. CQA reference arms are identified as reused controls and are not merged into the main results. 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 generative-control GPT-5, generative | 73.8 | |
| 2 | DecisionRAG generative-control + dense candidates | 73.4 | |
| 3 | DecisionRAG generative-control DecisionRAG | 69.7 |
Interactive version: theaggregate.ai/benchmark?slug=decisionrag-generative-control-cqa-hit-1 · How It Works · Data refreshed daily, snapshot 2026-10-28.