CoreCognition Image only Boundary: leaderboard

CoreCognition Image only 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: Rough model projection: around 2026. 77 models tracked. Updated 16 Nov 2026.

Top models

#ModelScoreOverall rank
1GLM-4V-Plus91.67#1400
2wemm-chat-cn85.96
3Phi-3-Vision82.49#5517
4Ovis1.6-Gemma2-27B82.4#1833
5step-1o-turbo-vision82.12
6Bunny-Llama3-8B81.18#7560
7NVLM-D-72B80.99#2181
8Step-1.5V-mini80.99#2720
9GLM-4V-9B80.34#3333
10wemm-chat-2k-cn80.24
11Cambrian-8B78.65#6834
12internlm-xcomposer2-vl-7B78.65
13Cambrian-34B77.62#5295
14WeMM77.25#5473
15360VL-70B77.06#5987

Interactive version: theaggregate.ai/benchmark?slug=corecognition-image-only-boundary · How It Works · Data refreshed daily, snapshot 2026-11-16.