SVFSearch - RAG Workflow: leaderboard
A fixed retrieval workflow (image retrieval, element voting, then text retrieval from a frozen offline knowledge base) on SVFSearch (2026), four-choice questions about paused frames of Chinese gaming short videos that need game-specific knowledge, over its 5,000-question test split. Accuracy in percent; higher is better.
Metric: Accuracy (%) on the 5,000-item SVFSearch test split (four-choice questions about a paused Chinese game video frame), given only the frame, question and options, with the fixed RAG workflow (image retrieval over the frozen game image index, element voting, then top-5 text retrieval) whose evidence is given to the model; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 5 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Qwen 3.5 27B | Non-reasoning | 69.4 | #375 |
| 2 | Qwen 3.5 9B | Non-reasoning | 66.5 | #828 |
| 3 | Qwen 3 VL 8B | 63.5 | #917 | |
| 4 | Qwen 3 VL 32B | 62.2 | #622 | |
| 5 | Qwen 2.5 VL 7B | 57.3 | #1862 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=svfsearch-rag-workflow · How It Works · Data refreshed daily, snapshot 2026-11-21.