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

#ModelScoreOverall rank
1cogvlm2-llama3-chat-19B68.1
2Monkey67.24#8891
3WeMM65.52#5473
4TransCore-M64.66#8171
5GLM-4V-9B63.79#3333
6Molmo-7B-D-092463.79#7502
7aquila-vl-2B-llava-qwen63.22
8Bunny-Llama3-8B62.07#7560
9Monkey-Chat61.78#7874
10llava-v1.5-13B-xtuner61.49
11Yi-VL-34B60.92#6990
12RekaFlash60.92#4203
13Llama-3-MixSense-v1.160.63#7268
14parrot-14B60.63
15Cambrian-34B60.34#5295

Interactive version: theaggregate.ai/benchmark?slug=corecognition-image-only-intuitivephysics · How It Works · Data refreshed daily, snapshot 2026-11-16.