CoreCognition Image only Boundary: leaderboard
CoreCognition Image only Boundary — 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 | 91.67 | #1400 |
| 2 | wemm-chat-cn | 85.96 | |
| 3 | Phi-3-Vision | 82.49 | #5517 |
| 4 | Ovis1.6-Gemma2-27B | 82.4 | #1833 |
| 5 | step-1o-turbo-vision | 82.12 | |
| 6 | Bunny-Llama3-8B | 81.18 | #7560 |
| 7 | NVLM-D-72B | 80.99 | #2181 |
| 8 | Step-1.5V-mini | 80.99 | #2720 |
| 9 | GLM-4V-9B | 80.34 | #3333 |
| 10 | wemm-chat-2k-cn | 80.24 | |
| 11 | Cambrian-8B | 78.65 | #6834 |
| 12 | internlm-xcomposer2-vl-7B | 78.65 | |
| 13 | Cambrian-34B | 77.62 | #5295 |
| 14 | WeMM | 77.25 | #5473 |
| 15 | 360VL-70B | 77.06 | #5987 |
Interactive version: theaggregate.ai/benchmark?slug=corecognition-image-only-boundary · How It Works · Data refreshed daily, snapshot 2026-11-16.