CoreCognition Single Image Spatiality: leaderboard
CoreCognition Single Image Spatiality — 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 | LLaVA-Video-7B-Qwen2 | 70.83 | #1854 | |
| 2 | llava-video-7B-qwen2-video-only | 66.67 | ||
| 3 | InternVL2.5-78B | 63.37 | #1044 | |
| 4 | qwen2.5-vl-7b-instruct_video | CoreCognition run: native-setting=qwen2.5-vl-7b-instruct_video | 61.11 | |
| 5 | qwen2.5-vl-3b-instruct_video | CoreCognition run: native-setting=qwen2.5-vl-3b-instruct_video | 60.76 | |
| 6 | InternVL2.5-26B | 59.55 | #2269 | |
| 7 | Video-LLaVA-7B | 59.55 | #3284 | |
| 8 | qwen2.5-vl-72b-instruct_video | CoreCognition run: native-setting=qwen2.5-vl-72b-instruct_video | 56.6 | |
| 9 | InternVL2.5-38B | 56.42 | #1413 | |
| 10 | chat-univi | 56.42 | ||
| 11 | llava-next-video-32B-qwen | 56.08 | ||
| 12 | PLLaVA-13B | 55.86 | #3155 | |
| 13 | InternVL2.5-4B | 53.99 | #2583 | |
| 14 | VideoLLaMA2-7B | 53.99 | #2213 | |
| 15 | InternVL2.5-8B | 53.13 | #2444 |
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-spatiality · How It Works · Data refreshed daily, snapshot 2026-11-16.