CoreCognition Image only Spatiality: leaderboard
CoreCognition Image only Spatiality — 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 | Molmo-72B-0924 | 81.06 | #5272 |
| 2 | Step-1.5V-mini | 74.62 | #2720 |
| 3 | step-1o-turbo-vision | 74.62 | |
| 4 | Molmo-7B-D-0924 | 74.05 | #7502 |
| 5 | points-qwen-2.5-7B-chat | 71.43 | |
| 6 | Llama-3-MixSense-v1.1 | 71.02 | #7268 |
| 7 | Molmo 7B-O | 70.45 | #6979 |
| 8 | NVLM-D-72B | 69.7 | #2181 |
| 9 | Cambrian-13B | 69.7 | #7053 |
| 10 | step-1v-32k | 69.13 | |
| 11 | Ovis1.6-Gemma2-27B | 67.99 | #1833 |
| 12 | Cambrian-34B | 67.23 | #5295 |
| 13 | Monkey | 65.53 | #8891 |
| 14 | GLM-4V | 65.34 | #3924 |
| 15 | llava-internlm-7B | 65.34 |
Interactive version: theaggregate.ai/benchmark?slug=corecognition-image-only-spatiality · How It Works · Data refreshed daily, snapshot 2026-11-16.