Video-MME-v2 - Level 1 Retrieval & Aggregation (w/o subs): leaderboard
Video-MME-v2 group score without subtitles on level 1, retrieving and aggregating information across the video. Video-MME-v2 groups four interrelated questions and scores each group non-linearly, so credit depends on consistency and a complete reasoning chain, not only per-question accuracy. 0-100, higher is better; same run per model as the headline board.
Metric: Level 1 Score w/o sub (%). Source: video-mme-v2.netlify.app. Saturation forecast: Around April 2027. 49 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Pro | 43.23 | #82 |
| 2 | Gemini 3 Flash | 41.48 | #103 |
| 3 | Doubao-Seed-2.0-Pro-260215 | 41.32 | #86 |
| 4 | Kimi K2.5 | 41.05 | #152 |
| 5 | GPT-5 | 32.15 | #105 |
| 6 | Gemma 4 31B | 21.51 | #212 |
| 7 | Qwen 3 VL 235B A22B (Thinking) | 21.36 | #236 |
| 8 | Qwen 3.5 Omni Plus | 21.25 | #111 |
| 9 | Qwen 3 VL 235B A22B Instruct | 20.65 | #280 |
| 10 | Qwen 3 VL 8B (Thinking) | 16.97 | #423 |
| 11 | Qwen 3 VL 30B A3B (Thinking) | 16.94 | #348 |
| 12 | Qwen 3 VL 4B Instruct | 16.35 | #510 |
| 13 | Qwen 3 VL 8B Instruct | 15.37 | #419 |
| 14 | Qwen 2.5 VL 72B Instruct | 15.32 | #383 |
| 15 | Qwen3 Omni 30B A3B Instruct | 15.02 | #401 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=video-mme-v2-level-1-retrieval-aggregation-w-o-subs · How It Works · Data refreshed daily, snapshot 2026-11-05.