CoreCognition Single Image Boundary: leaderboard
CoreCognition Single Image Boundary — 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 | VideoLLaMA2-72B | 85.11 | #1355 | |
| 2 | llava-video-7B-qwen2-video-only | 82.49 | ||
| 3 | LLaVA-Video-7B-Qwen2 | 82.3 | #1854 | |
| 4 | qwen2.5-vl-7b-instruct_video | CoreCognition run: native-setting=qwen2.5-vl-7b-instruct_video | 82.3 | |
| 5 | LLaVA-Video-72B-Qwen2 | 81.46 | #1228 | |
| 6 | InternVL2.5-78B | 80.81 | #1044 | |
| 7 | InternVL2.5-38B | 80.24 | #1413 | |
| 8 | yi-vision-v2 | 79.87 | ||
| 9 | qwen2.5-vl-72b-instruct_video | CoreCognition run: native-setting=qwen2.5-vl-72b-instruct_video | 79.59 | |
| 10 | InternVL2.5-2B | 77.62 | #6932 | |
| 11 | llava-next-video-32B-qwen | 75.84 | ||
| 12 | videollama2-7B-16f | 74.16 | ||
| 13 | LLaVA-CoT | 72.85 | #3271 | |
| 14 | InternVL2.5-4B | 72.57 | #2583 | |
| 15 | InternVL2.5-26B | 72.38 | #2269 |
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-boundary · How It Works · Data refreshed daily, snapshot 2026-11-16.