CoreCognition Single Image Intuitivephysics: leaderboard
CoreCognition Single Image Intuitivephysics — 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 | 64.55 | |
| 2 | qwen2.5-vl-3b-instruct_video | CoreCognition run: native-setting=qwen2.5-vl-3b-instruct_video | 61.52 | |
| 3 | InternVL2.5-26B | 60.91 | #2269 | |
| 4 | InternVL2.5-78B | 59.7 | #1044 | |
| 5 | VideoLLaMA2.1-7B-16F | 59.09 | #1924 | |
| 6 | qwen2.5-vl-7b-instruct_video | CoreCognition run: native-setting=qwen2.5-vl-7b-instruct_video | 58.79 | |
| 7 | LLaVA-Video-72B-Qwen2 | 57.88 | #1228 | |
| 8 | InternVL2.5-4B | 57.27 | #2583 | |
| 9 | Llama 3.2 11B Instruct | 56.97 | #5235 | |
| 10 | llava-video-7B-qwen2-video-only | 56.36 | ||
| 11 | InternVL2.5-2B | 54.39 | #6932 | |
| 12 | VideoLLaMA2-72B | 53.33 | #1355 | |
| 13 | InternVL2.5-38B | 52.58 | #1413 | |
| 14 | Llama 3.2 90B Vision Instruct | 51.97 | #1769 | |
| 15 | chat-univi | 51.97 |
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-intuitivephysics · How It Works · Data refreshed daily, snapshot 2026-11-16.