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
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | 360VL-70B | 70.31 | #5987 |
| 2 | Cambrian-34B | 69.09 | #5295 |
| 3 | wemm-chat-2k-cn | 68.2 | |
| 4 | step-1v-32k | 68.04 | |
| 5 | points-qwen-2.5-7B-chat | 67.8 | |
| 6 | Cambrian-8B | 67.07 | #6834 |
| 7 | WeMM | 66.99 | #5473 |
| 8 | wemm-chat-cn | 65.86 | |
| 9 | Ovis1.6-Gemma2-27B | 65.7 | #1833 |
| 10 | mgm-7B-hd | 65.37 | |
| 11 | NVLM-D-72B | 64.48 | #2181 |
| 12 | omchat | 63.03 | |
| 13 | Llama-3-MixSense-v1.1 | 62.94 | #7268 |
| 14 | GLM-4V-Plus | 62.86 | #1400 |
| 15 | aquila-vl-2B-llava-qwen | 62.78 |
Interactive version: theaggregate.ai/benchmark?slug=corecognition-image-only-hierarchy · How It Works · Data refreshed daily, snapshot 2026-11-16.