CoreCognition Single Image Hierarchy: leaderboard
CoreCognition Single Image 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. 33 models tracked. Updated 16 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | qwen2.5-vl-72b-instruct_video | CoreCognition run: native-setting=qwen2.5-vl-72b-instruct_video | 68.45 | |
| 2 | LLaVA-Video-72B-Qwen2 | 66.1 | #1228 | |
| 3 | yi-vision-v2 | 64.64 | ||
| 4 | qwen2.5-vl-7b-instruct_video | CoreCognition run: native-setting=qwen2.5-vl-7b-instruct_video | 62.38 | |
| 5 | VideoLLaMA2-72B | 61.73 | #1355 | |
| 6 | qwen2.5-vl-3b-instruct_video | CoreCognition run: native-setting=qwen2.5-vl-3b-instruct_video | 60.84 | |
| 7 | InternVL2.5-78B | 60.52 | #1044 | |
| 8 | Llama 3.2 90B Vision Instruct | 59.87 | #1769 | |
| 9 | InternVL2.5-26B | 59.87 | #2269 | |
| 10 | LLaVA-Video-7B-Qwen2 | 59.87 | #1854 | |
| 11 | LLaVA-CoT | 57.69 | #3271 | |
| 12 | InternVL2.5-8B | 56.15 | #2444 | |
| 13 | VideoLLaMA2.1-7B-16F | 55.99 | #1924 | |
| 14 | InternVL2.5-4B | 53.8 | #2583 | |
| 15 | videochat2-stage3-mistral-7B | 51.62 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=corecognition-single-image-hierarchy · How It Works · Data refreshed daily, snapshot 2026-11-16.