CoreCognition Single Image Permanence: leaderboard
CoreCognition Single Image 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. 33 models tracked. Updated 16 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | videochat2-stage3-mistral-7B | 48.69 | ||
| 2 | videollama2-7B-16f | 45.26 | ||
| 3 | chat-univi-13B | 45.26 | ||
| 4 | chat-univi | 44.61 | ||
| 5 | LLaVA-CoT | 43.95 | #3271 | |
| 6 | LLaVA-Video-72B-Qwen2 | 42.89 | #1228 | |
| 7 | InternVL2.5-78B | 41.09 | #1044 | |
| 8 | InternVL2.5-8B | 40.85 | #2444 | |
| 9 | VideoLLaMA2-7B | 40.85 | #2213 | |
| 10 | video-chat-13B | 40.85 | ||
| 11 | qwen2.5-vl-7b-instruct_video | CoreCognition run: native-setting=qwen2.5-vl-7b-instruct_video | 40.2 | |
| 12 | qwen2.5-vl-72b-instruct_video | CoreCognition run: native-setting=qwen2.5-vl-72b-instruct_video | 38.81 | |
| 13 | VideoLLaMA2-72B | 38.24 | #1355 | |
| 14 | llava-video-7B-qwen2-video-only | 37.99 | ||
| 15 | InternVL2.5-38B | 37.91 | #1413 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=corecognition-single-image-permanence · How It Works · Data refreshed daily, snapshot 2026-11-16.