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

#ModelSettingScoreOverall rank
1LLaVA-Video-7B-Qwen270.83#1854
2llava-video-7B-qwen2-video-only66.67
3InternVL2.5-78B63.37#1044
4qwen2.5-vl-7b-instruct_videoCoreCognition run: native-setting=qwen2.5-vl-7b-instruct_video61.11
5qwen2.5-vl-3b-instruct_videoCoreCognition run: native-setting=qwen2.5-vl-3b-instruct_video60.76
6InternVL2.5-26B59.55#2269
7Video-LLaVA-7B59.55#3284
8qwen2.5-vl-72b-instruct_videoCoreCognition run: native-setting=qwen2.5-vl-72b-instruct_video56.6
9InternVL2.5-38B56.42#1413
10chat-univi56.42
11llava-next-video-32B-qwen56.08
12PLLaVA-13B55.86#3155
13InternVL2.5-4B53.99#2583
14VideoLLaMA2-7B53.99#2213
15InternVL2.5-8B53.13#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.