CoreCognition Image only Hierarchy: leaderboard

CoreCognition Image only Hierarchy — 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
1360VL-70B70.31#5987
2Cambrian-34B69.09#5295
3wemm-chat-2k-cn68.2
4step-1v-32k68.04
5points-qwen-2.5-7B-chat67.8
6Cambrian-8B67.07#6834
7WeMM66.99#5473
8wemm-chat-cn65.86
9Ovis1.6-Gemma2-27B65.7#1833
10mgm-7B-hd65.37
11NVLM-D-72B64.48#2181
12omchat63.03
13Llama-3-MixSense-v1.162.94#7268
14GLM-4V-Plus62.86#1400
15aquila-vl-2B-llava-qwen62.78

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