CoreCognition Image + Video Spatiality: leaderboard

CoreCognition Image + Video Spatiality — 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
1Gemini 1.5 Flash68.11#1694
2GPT-4o67.95#744
3Gemini 1.5 Pro67.95#1061
4Grok 2 (1212)67.63#1072
5Claude 3.5 Sonnet (20240620)64.74#692
6Qwen 2.5 VL 7B Instruct63.78#1867
7Qwen-VL-Plus-2025-01-2563.35
8Qwen 2.5 VL 72B Instruct62.82#848
9Qwen-VL-Max-2025-01-2561.56
10DeepSeek-VL2-Small61.3#2401
11O1 (2024-12-17)61.22#313
12VILA1.5-40B59.7#3222
13llava-video-7b-qwen2_multi_frameCoreCognition run: native-setting=llava-video-7b-qwen2_multi_frame56.41
14InternVL2-26B55.61#2617
15Claude 3.7 Sonnet (20250219)55.29#414

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-spatiality · How It Works · Data refreshed daily, snapshot 2026-11-16.