CoreCognition Single Image Perspective: leaderboard

CoreCognition Single Image Perspective — 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

#ModelScoreOverall rank
1chat-univi49.14
2PLLaVA-13B46.7#3155
3Video-LLaVA-7B46.69#3284
4PLLaVA-7B45.03#5036
5video-chat-13B43.95
6VideoLLaMA2-7B43.04#2213
7chat-univi-13B42.64
8Llama 3.2 11B Instruct41.1#5235
9videochat2_hd_stage4_mistral_7b_hf40.7
10VideoLLaMA2.1-7B-16F38.07#1924
11InternVL2.5-2B37.9#6932
12videochat2-stage3-mistral-7B37.79
13InternVL2.5-4B37.04#2583
14VideoChat-7B35.96
15Llama 3.2 90B Vision Instruct35.56#1769

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