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
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | MiniCPM-V-2.6 | 77.33 | #3243 | |
| 2 | Mantis-8B-Idefics2 | 73.26 | #6912 | |
| 3 | XinYuan-VL-2B-Instruct | 72.38 | #5714 | |
| 4 | Qwen 2 VL 72B Instruct | 71.51 | #1388 | |
| 5 | Gemini 1.5 Flash | 71.22 | #1694 | |
| 6 | XGen-MM-Instruct-DPO-v1.5 | 70.93 | #7079 | |
| 7 | GPT-4o Mini | 70.06 | #1658 | |
| 8 | InternVL2-40B | 70.06 | #2106 | |
| 9 | InternVL2-26B | 69.77 | #2617 | |
| 10 | InternVL2-8B-MPO | 69.77 | #4132 | |
| 11 | MiniCPM-Llama3-V2.5 | 69.77 | #5149 | |
| 12 | internvl2-8b-mpo-cot | CoreCognition run: native-setting=internvl2-8b-mpo-cot | 69.77 | |
| 13 | Gemini 1.5 Pro | 69.19 | #1061 | |
| 14 | Grok 2 (1212) | 69.19 | #1072 | |
| 15 | InternVL2-76B | 69.19 | #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.