CoreCognition Image only Conservation: leaderboard
CoreCognition Image only Conservation — 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 | Yi-VL-34B | 69.21 | #6990 |
| 2 | cogvlm-grounding-generalist | 67.94 | |
| 3 | ShareGPT4V-13B | 67.62 | #8424 |
| 4 | wemm-chat-2k-cn | 67.62 | |
| 5 | visualglm-6B | 66.98 | |
| 6 | fuyu-8B | 66.98 | |
| 7 | instructblip-flan-t5-xl | 66.67 | |
| 8 | step-1o-turbo-vision | 66.35 | |
| 9 | InstructBLIP-Flan-T5-XXL | 66.03 | |
| 10 | InternLM-XComposer2-4KHD | 65.71 | #6477 |
| 11 | InstructBLIP-Vicuna-7B | 65.4 | |
| 12 | smolvlm-dpo | 65.08 | |
| 13 | Cambrian-8B | 64.76 | #6834 |
| 14 | mgm-7B-hd | 64.44 | |
| 15 | omchat | 64.44 |
Interactive version: theaggregate.ai/benchmark?slug=corecognition-image-only-conservation · How It Works · Data refreshed daily, snapshot 2026-11-16.