CoreCognition Single Image Boundary: leaderboard

CoreCognition Single Image Boundary — 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
1VideoLLaMA2-72B85.11#1355
2llava-video-7B-qwen2-video-only82.49
3LLaVA-Video-7B-Qwen282.3#1854
4qwen2.5-vl-7b-instruct_videoCoreCognition run: native-setting=qwen2.5-vl-7b-instruct_video82.3
5LLaVA-Video-72B-Qwen281.46#1228
6InternVL2.5-78B80.81#1044
7InternVL2.5-38B80.24#1413
8yi-vision-v279.87
9qwen2.5-vl-72b-instruct_videoCoreCognition run: native-setting=qwen2.5-vl-72b-instruct_video79.59
10InternVL2.5-2B77.62#6932
11llava-next-video-32B-qwen75.84
12videollama2-7B-16f74.16
13LLaVA-CoT72.85#3271
14InternVL2.5-4B72.57#2583
15InternVL2.5-26B72.38#2269

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