CoreCognition Single Image Perceptualconstancy: leaderboard
CoreCognition Single Image 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: Estimated already saturated. 33 models tracked. Updated 16 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | qwen2.5-vl-72b-instruct_video | CoreCognition run: native-setting=qwen2.5-vl-72b-instruct_video | 84.69 | |
| 2 | llava-next-video-32B-qwen | 72.38 | ||
| 3 | InternVL2.5-78B | 72.29 | #1044 | |
| 4 | LLaVA-Video-7B-Qwen2 | 72.09 | #1854 | |
| 5 | LLaVA-Video-72B-Qwen2 | 71.51 | #1228 | |
| 6 | VideoLLaMA2-72B | 68.41 | #1355 | |
| 7 | qwen2.5-vl-7b-instruct_video | CoreCognition run: native-setting=qwen2.5-vl-7b-instruct_video | 68.02 | |
| 8 | yi-vision-v2 | 67.64 | ||
| 9 | LLaVA-CoT | 67.34 | #3271 | |
| 10 | InternVL2.5-26B | 66.86 | #2269 | |
| 11 | videollama2-7B-16f | 65.99 | ||
| 12 | VideoLLaMA2.1-7B-16F | 65.12 | #1924 | |
| 13 | InternVL2.5-4B | 64.53 | #2583 | |
| 14 | qwen2.5-vl-3b-instruct_video | CoreCognition run: native-setting=qwen2.5-vl-3b-instruct_video | 64.34 | |
| 15 | Llama 3.2 90B Vision Instruct | 62.21 | #1769 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=corecognition-single-image-perceptualconstancy · How It Works · Data refreshed daily, snapshot 2026-11-16.