CoreCognition Single Image Perspective: leaderboard
CoreCognition Single Image 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. 33 models tracked. Updated 16 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | chat-univi | 49.14 | |
| 2 | PLLaVA-13B | 46.7 | #3155 |
| 3 | Video-LLaVA-7B | 46.69 | #3284 |
| 4 | PLLaVA-7B | 45.03 | #5036 |
| 5 | video-chat-13B | 43.95 | |
| 6 | VideoLLaMA2-7B | 43.04 | #2213 |
| 7 | chat-univi-13B | 42.64 | |
| 8 | Llama 3.2 11B Instruct | 41.1 | #5235 |
| 9 | videochat2_hd_stage4_mistral_7b_hf | 40.7 | |
| 10 | VideoLLaMA2.1-7B-16F | 38.07 | #1924 |
| 11 | InternVL2.5-2B | 37.9 | #6932 |
| 12 | videochat2-stage3-mistral-7B | 37.79 | |
| 13 | InternVL2.5-4B | 37.04 | #2583 |
| 14 | VideoChat-7B | 35.96 | |
| 15 | Llama 3.2 90B Vision Instruct | 35.56 | #1769 |
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-perspective · How It Works · Data refreshed daily, snapshot 2026-11-16.