CoreCognition Image + Video Intuitivephysics: leaderboard
CoreCognition Image + Video 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. 120 models tracked. Updated 16 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | O1 (2024-12-17) | 75.45 | #313 | |
| 2 | Idefics3-8B-Llama3 | 65.3 | #5972 | |
| 3 | GPT-4 Turbo | 63.48 | #999 | |
| 4 | Qwen 2.5 VL 3B Instruct | 62.12 | #2562 | |
| 5 | Qwen 2 VL 7B Instruct | 61.82 | #2596 | |
| 6 | Ovis1.6-Llama3.2-3B | 61.36 | #3459 | |
| 7 | internvl-chat-v1-1 | 61.06 | ||
| 8 | VILA1.5-13B | 60.76 | #7184 | |
| 9 | Phi-3.5-Vision | 60.61 | #4877 | |
| 10 | llama-3-vila1.5-8b-fix | CoreCognition run | 60.61 | |
| 11 | Qwen 2 VL 2B Instruct | 60.45 | #4986 | |
| 12 | InternVL2-76B | 60.15 | #1519 | |
| 13 | Mini-InternVL-Chat-4B-V1.5 | 60 | #4881 | |
| 14 | IDEFICS-80B-Instruct | 59.85 | #8917 | |
| 15 | DeepSeek-VL2-Small | 59.85 | #2401 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=corecognition-image-plus-video-intuitivephysics · How It Works · Data refreshed daily, snapshot 2026-11-16.