CoreCognition Image + Video Boundary: leaderboard
CoreCognition Image + Video 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. 120 models tracked. Updated 16 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | GPT-4o | 87.17 | #744 | |
| 2 | llava-video-7b-qwen2_multi_frame | CoreCognition run: native-setting=llava-video-7b-qwen2_multi_frame | 86.52 | |
| 3 | Ovis1.6-Gemma2-9B | 85.39 | #2314 | |
| 4 | LLaVA-LLaMA-3-8B | 85.11 | #7395 | |
| 5 | Qwen 2 VL 7B Instruct | 83.99 | #2596 | |
| 6 | Claude 3.7 Sonnet (20250219) | 82.87 | #414 | |
| 7 | DeepSeek-VL2-Small | 82.68 | #2401 | |
| 8 | Gemini 1.5 Pro | 82.58 | #1061 | |
| 9 | llava-video-7b-qwen2-video-only_multi_frame | CoreCognition run: native-setting=llava-video-7b-qwen2-video-only_multi_frame | 82.49 | |
| 10 | eagle-x5-13B-chat | 82.49 | ||
| 11 | Qwen-VL-Max-2025-01-25 | 82.4 | ||
| 12 | Qwen 2.5 VL 7B Instruct | 82.3 | #1867 | |
| 13 | internvl-chat-v1-2-plus | 82.3 | ||
| 14 | internvl-chat-v1-2 | 82.02 | ||
| 15 | DeepSeek-VL-7B-Chat | 81.84 | #3413 |
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-boundary · How It Works · Data refreshed daily, snapshot 2026-11-16.