CoreCognition Image + Video Perceptualconstancy: leaderboard

CoreCognition Image + Video 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. 120 models tracked. Updated 16 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1O1 (2024-12-17)87.79#313
2Qwen 2.5 VL 72B Instruct85.27#848
3Qwen-VL-Max-2025-01-2584.33
4GPT-4 Turbo82.17#999
5GPT-4o81.2#744
6Qwen 2 VL 72B Instruct80.81#1388
7Gemini 1.5 Flash77.62#1694
8XGen-MM-Instruct-Interleave-v1.577.33#7042
9XGen-MM-Instruct-DPO-v1.577.13#7079
10Claude 3.5 Sonnet (20240620)76.74#692
11Claude 3 Opus (20240229)76.55#1125
12llava-video-7b-qwen2_multi_frameCoreCognition run: native-setting=llava-video-7b-qwen2_multi_frame76.16
13Gemini 1.5 Flash-8B75.97#2670
14Claude 3.7 Sonnet (20250219)75#414
15DeepSeek-VL2-Small75#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-perceptualconstancy · How It Works · Data refreshed daily, snapshot 2026-11-16.