CoreCognition Image only Perceptualconstancy: leaderboard
CoreCognition Image only Perceptualconstancy — 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 | 80.42 | #1400 |
| 2 | Cambrian-8B | 77.62 | #6834 |
| 3 | step-1o-turbo-vision | 76.69 | |
| 4 | Cambrian-34B | 76.46 | #5295 |
| 5 | IDEFICS2-8B | 74.83 | #5096 |
| 6 | Step-1.5V-mini | 73.19 | #2720 |
| 7 | 360VL-70B | 72.03 | #5987 |
| 8 | InternLM-XComposer2-4KHD | 69.7 | #6477 |
| 9 | InternLM-XComposer2-1.8B | 69.23 | #8431 |
| 10 | PaliGemma-3B-mix-448 | 68.65 | #6985 |
| 11 | Phi-3-Vision | 68.3 | #5517 |
| 12 | points-qwen-2.5-7B-chat | 68.3 | |
| 13 | NVLM-D-72B | 68.18 | #2181 |
| 14 | wemm-chat-2k-cn | 67.37 | |
| 15 | Monkey-Chat | 67.13 | #7874 |
Interactive version: theaggregate.ai/benchmark?slug=corecognition-image-only-perceptualconstancy · How It Works · Data refreshed daily, snapshot 2026-11-16.