SuperMemory-VQA (Video-RAG) - Answerable F1: leaderboard
Metric: Binary answerable-vs-unanswerable F1 (%) under Video-RAG; higher is better. Source: arxiv.org. Saturation forecast: Around December 2026. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Flash | 83.9 |
| 2 | InternVL3.5-8B | 81.7 |
| 3 | GPT-5.4 | 78.3 |
| 4 | GPT-5.4 Mini | 77.6 |
| 5 | Gemini 3.1 Pro (Preview) | 67.4 |
| 6 | Gemma 4 31B (IT) | 67.2 |
| 7 | gemma-4-E4B-it | 40.3 |
Interactive version: theaggregate.ai/benchmark?slug=supermemory-vqa-video-rag-answerable-f1 · How It Works · Data refreshed daily, snapshot 2026-09-29.