CoreCognition Image + Video Permanence: leaderboard
CoreCognition Image + Video Permanence — CoreCognition native component accuracy and reported mean. Image+Video, image-only and single-image populations are separate; no pooling or replacement across cohorts. Metric: Accuracy (%). Source: https://grow-ai-like-a-child.github.io/CoreCognition/leaderboard
Metric: Accuracy (%). Source: grow-ai-like-a-child.github.io. Saturation forecast: Estimated already saturated. 120 models tracked. Updated 16 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | LLaVA-NeXT-72B | 61.03 | #3185 | |
| 2 | Gemini 1.5 Pro | 59.56 | #1061 | |
| 3 | Gemma 3 4B (IT) | 58.66 | #4078 | |
| 4 | Llama-3-VILA1.5-8B | 58.09 | #7424 | |
| 5 | Gemini 1.5 Flash-8B | 58.01 | #2670 | |
| 6 | O1 (2024-12-17) | 57.03 | #313 | |
| 7 | llama-3-longvila-8b-1024frames | CoreCognition run: native-setting=llama-3-longvila-8b-1024frames | 55.88 | |
| 8 | llama-3-longvila-8b-256frames | CoreCognition run: native-setting=llama-3-longvila-8b-256frames | 54.41 | |
| 9 | MiniCPM-Llama3-V2.5 | 54.17 | #5149 | |
| 10 | llama-3-longvila-8b-512frames | CoreCognition run: native-setting=llama-3-longvila-8b-512frames | 54.17 | |
| 11 | internvl-chat-v1-2 | 53.21 | ||
| 12 | InternLM-XComposer2.5 | 53.1 | #3981 | |
| 13 | GPT-4o | 52.86 | #744 | |
| 14 | Mini-InternVL-Chat-4B-V1.5 | 51.47 | #4881 | |
| 15 | llama-3-longvila-8b-128frames | CoreCognition run: native-setting=llama-3-longvila-8b-128frames | 50.98 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=corecognition-image-plus-video-permanence · How It Works · Data refreshed daily, snapshot 2026-11-16.