CoreCognition Image only Continuity: leaderboard
CoreCognition Image only 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: Rough model projection: around 2026. 77 models tracked. Updated 16 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GLM-4V-Plus | 81.64 | #1400 |
| 2 | GLM-4V-9B | 80.47 | #3333 |
| 3 | internlm-xcomposer2-vl-7B | 78.91 | |
| 4 | Cambrian-8B | 76.95 | #6834 |
| 5 | Cambrian-13B | 75.78 | #7053 |
| 6 | Emu3-Chat | 75.39 | #8806 |
| 7 | Cambrian-34B | 74.22 | #5295 |
| 8 | Step-1.5V-mini | 71.88 | #2720 |
| 9 | InternLM-XComposer2-4KHD | 71.48 | #6477 |
| 10 | points-qwen-2.5-7B-chat | 71.43 | |
| 11 | IDEFICS2-8B | 71.09 | #5096 |
| 12 | GLM-4V | 70.7 | #3924 |
| 13 | Ovis1.6-Gemma2-27B | 70.31 | #1833 |
| 14 | Moondream2 | 70.31 | #8961 |
| 15 | mgm-7B-hd | 70.31 |
Interactive version: theaggregate.ai/benchmark?slug=corecognition-image-only-continuity · How It Works · Data refreshed daily, snapshot 2026-11-16.