VSAS-Bench (Synchronous) - Future: leaderboard
VSAS-Bench (2026) Future tasks, which ask the model to anticipate upcoming events from ongoing visual cues in a streamed video, under the synchronous protocol; per-timestep responses judged against dense reference annotations, accuracy (%), higher is better.
Metric: Mean average accuracy (%) on Future tasks (predicting upcoming events from current cues) under the synchronous protocol (the model runs in lockstep with the stream, so inference latency does not count; video VLMs adapted with the sliding-window memory policy), over VSAS-Bench's 92 videos with dense 1 FPS free-form annotations; each timestep's response is judged against the annotation by GPT-5 (medium reasoning) on a 0-1 scale, shown as %; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 12 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | GPT-5 | High | 85.1 | #178 |
| 2 | Dispider | 66.6 | #3815 | |
| 3 | Qwen 3 VL 8B Instruct | 35.5 | #1029 | |
| 4 | InternVL3-38B | 34.7 | #939 | |
| 5 | Qwen 3 VL 32B Instruct | 31.4 | #606 | |
| 6 | Qwen 3 VL 4B Instruct | 19.5 | #1332 | |
| 7 | InternVL3-8B | 14.6 | #1782 | |
| 8 | StreamBridge [VSAS-Bench checkpoint unspecified] | 14.1 | ||
| 9 | Qwen 3 VL 2B Instruct | 13.1 | #2367 | |
| 10 | InternVL3-2B | 13 | #3290 | |
| 11 | Flash-VStream-7B | 8.7 | ||
| 12 | VideoLLM-Online | 2.3 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=vsas-bench-synchronous-future · How It Works · Data refreshed daily, snapshot 2026-11-21.