CoreCognition Single Image Continuity: leaderboard

CoreCognition Single Image Continuity — 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
1videochat2_hd_stage4_mistral_7b_hf70.64
2videochat2-stage3-mistral-7B69.19
3qwen2.5-vl-72b-instruct_videoCoreCognition run: native-setting=qwen2.5-vl-72b-instruct_video66.86
4InternVL2.5-38B66.57#1413
5InternVL2.5-26B66.57#2269
6VideoLLaMA2.1-7B-16F66.28#1924
7llava-next-video-32B-qwen66.09
8LLaVA-Video-7B-Qwen263.79#1854
9yi-vision-v263.08
10videollama2-7B-16f62.79
11Llama 3.2 11B Instruct61.63#5235
12Llama 3.2 90B Vision Instruct61.63#1769
13VideoLLaMA2-72B61.63#1355
14qwen2.5-vl-3b-instruct_videoCoreCognition run: native-setting=qwen2.5-vl-3b-instruct_video61.05
15qwen2.5-vl-7b-instruct_videoCoreCognition run: native-setting=qwen2.5-vl-7b-instruct_video60.76

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-continuity · How It Works · Data refreshed daily, snapshot 2026-11-16.