SVFSearch - Plan-Act-Replan Agent: leaderboard
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, as a LangGraph Plan-Act-Replan agent choosing among image, text, BM25 and multimodal retrieval over the frozen offline resources (top-5, up to six rounds with one tool call each); higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.5 9B (Non-reasoning) | 79.1 |
| 2 | Qwen 3.5 27B (Non-reasoning) | 78.6 |
| 3 | Qwen 2.5 VL 7B | 59.3 |
Interactive version: theaggregate.ai/benchmark?slug=svfsearch-plan-act-replan-agent · How It Works · Data refreshed daily, snapshot 2026-10-07.