CoreCognition Image + Video Hierarchy: leaderboard

CoreCognition Image + Video Hierarchy — 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)75.49#313
2Qwen 2 VL 7B Instruct75.08#2596
3Qwen 2 VL 72B Instruct74.68#1388
4Gemini 1.5 Flash73.95#1694
5Gemini 1.5 Pro73.62#1061
6InternVL2-40B73.22#2106
7Ovis1.6-Gemma2-9B71.6#2314
8Claude 3.7 Sonnet (20250219)71.36#414
9llava-next-video-32b-qwen_multi_frameCoreCognition run: native-setting=llava-next-video-32b-qwen_multi_frame71.2
10Grok 2 (1212)71.12#1072
11eagle-x5-34B-plus70.95
12mPLUG-Owl370.63#2436
13Gemma 3 12B (IT)70.47#1884
14Mini-InternVL-Chat-4B-V1.569.82#4881
15Gemma 3 27B (IT)69.74#1322

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