Qwen3.8 Launch - VideoDR (with Search): leaderboard
VideoDR is a video deep-research benchmark: agents pick up visual cues across video frames, search the open web over several hops and combine both to answer a factual question. From the Qwen3.8-Max launch post's multimodal table, run with access to a search tool; score in percent, higher is better; Gemini 3.1 Pro has no cell.
Metric: Score (%). Source: qwen.ai. Saturation forecast: Around February 2027. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Fable 5 | 77.1 | #20 |
| 2 | Qwen 3.8 Max | 73.2 | #34 |
| 3 | GPT-5.6 Sol | 71.3 | #22 |
| 4 | Claude Opus 4.8 | 65.6 | #39 |
| 5 | Qwen 3.7 Plus | 41 | #98 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=qwen3-8-launch-videodr-with-search · How It Works · Data refreshed daily, snapshot 2026-11-05.