CoreCognition Image + Video Continuity: leaderboard

CoreCognition Image + Video Continuity — 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
1MiniCPM-V-2.677.33#3243
2Mantis-8B-Idefics273.26#6912
3XinYuan-VL-2B-Instruct72.38#5714
4Qwen 2 VL 72B Instruct71.51#1388
5Gemini 1.5 Flash71.22#1694
6XGen-MM-Instruct-DPO-v1.570.93#7079
7GPT-4o Mini70.06#1658
8InternVL2-40B70.06#2106
9InternVL2-26B69.77#2617
10InternVL2-8B-MPO69.77#4132
11MiniCPM-Llama3-V2.569.77#5149
12internvl2-8b-mpo-cotCoreCognition run: native-setting=internvl2-8b-mpo-cot69.77
13Gemini 1.5 Pro69.19#1061
14Grok 2 (1212)69.19#1072
15InternVL2-76B69.19#1519

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