CoreCognition Image + Video Perspective: leaderboard
CoreCognition Image + Video Perspective — 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 | O1 (2024-12-17) | 55.21 | #313 | |
| 2 | Qwen2.5-Omni-7B | 45.62 | #1866 | |
| 3 | IDEFICS-80B-Instruct | 44.37 | #8917 | |
| 4 | openflamingo-9B-vitl-mpt7B | 44.13 | ||
| 5 | InternVL2-1B | 43.62 | #8344 | |
| 6 | Vintern-1B-v2 | 43.62 | #8741 | |
| 7 | GPT-4 Turbo | 43.11 | #999 | |
| 8 | GPT-4o | 43.06 | #744 | |
| 9 | Claude 3 Sonnet (20240229) | 42.88 | #1963 | |
| 10 | Claude 3 Opus (20240229) | 42.5 | #1125 | |
| 11 | InternVL2-2B | 42.46 | #7256 | |
| 12 | Claude 3 Haiku (20240307) | 41.71 | #2380 | |
| 13 | qwen_chat | CoreCognition run | 41.67 | |
| 14 | janusflow-1.3B | 41.34 | ||
| 15 | vila1.5-3B-s2 | 41.11 |
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-perspective · How It Works · Data refreshed daily, snapshot 2026-11-16.