CoreCognition Image only Intuitivephysics: leaderboard
CoreCognition Image only 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: Rough model projection: around 2026. 77 models tracked. Updated 16 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | cogvlm2-llama3-chat-19B | 68.1 | |
| 2 | Monkey | 67.24 | #8891 |
| 3 | WeMM | 65.52 | #5473 |
| 4 | TransCore-M | 64.66 | #8171 |
| 5 | GLM-4V-9B | 63.79 | #3333 |
| 6 | Molmo-7B-D-0924 | 63.79 | #7502 |
| 7 | aquila-vl-2B-llava-qwen | 63.22 | |
| 8 | Bunny-Llama3-8B | 62.07 | #7560 |
| 9 | Monkey-Chat | 61.78 | #7874 |
| 10 | llava-v1.5-13B-xtuner | 61.49 | |
| 11 | Yi-VL-34B | 60.92 | #6990 |
| 12 | RekaFlash | 60.92 | #4203 |
| 13 | Llama-3-MixSense-v1.1 | 60.63 | #7268 |
| 14 | parrot-14B | 60.63 | |
| 15 | Cambrian-34B | 60.34 | #5295 |
Interactive version: theaggregate.ai/benchmark?slug=corecognition-image-only-intuitivephysics · How It Works · Data refreshed daily, snapshot 2026-11-16.