CoreCognition Single Image Conservation: leaderboard
CoreCognition Single Image Conservation — 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 | 80.78 | |
| 2 | InternVL2.5-78B | 65.47 | #1044 | |
| 3 | qwen2.5-vl-7b-instruct_video | CoreCognition run: native-setting=qwen2.5-vl-7b-instruct_video | 65.17 | |
| 4 | Llama 3.2 90B Vision Instruct | 64.56 | #1769 | |
| 5 | yi-vision-v2 | 59.16 | ||
| 6 | InternVL2.5-38B | 56.76 | #1413 | |
| 7 | qwen2.5-vl-3b-instruct_video | CoreCognition run: native-setting=qwen2.5-vl-3b-instruct_video | 54.95 | |
| 8 | InternVL2.5-8B | 54.35 | #2444 | |
| 9 | VideoChat-7B | 54.35 | ||
| 10 | LLaVA-Video-72B-Qwen2 | 54.05 | #1228 | |
| 11 | VideoLLaMA2-72B | 53.75 | #1355 | |
| 12 | video-chat-13B | 51.35 | ||
| 13 | LLaVA-Video-7B-Qwen2 | 51.05 | #1854 | |
| 14 | videollama2-7B-16f | 51.05 | ||
| 15 | VideoLLaMA2-7B | 48.05 | #2213 |
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-conservation · How It Works · Data refreshed daily, snapshot 2026-11-16.