CoreCognition Image + Video Intentionality: leaderboard
CoreCognition Image + Video Intentionality — 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 | Score | Overall rank |
|---|---|---|---|
| 1 | O1 (2024-12-17) | 87.54 | #313 |
| 2 | Qwen 2 VL 72B Instruct | 87.46 | #1388 |
| 3 | GPT-4o | 85.2 | #744 |
| 4 | LLaVA-NeXT-110B | 82.87 | #1954 |
| 5 | InternVL2-26B | 82.4 | #2617 |
| 6 | llava-onevision-qwen2-72B-si-hf | 82.4 | |
| 7 | InternVL2-76B | 82.24 | #1519 |
| 8 | llava-onevision-qwen2-72B-ov-chat-hf | 81.93 | #2654 |
| 9 | MMAlaya2 | 81.07 | #2886 |
| 10 | Gemini 1.5 Pro | 81 | #1061 |
| 11 | InternVL2-40B | 81 | #2106 |
| 12 | Qwen-VL-Max-2025-01-25 | 81 | |
| 13 | GPT-4 Turbo | 80.92 | #999 |
| 14 | internvl-chat-v1-2 | 80.86 | |
| 15 | Qwen 2.5 VL 72B Instruct | 80.45 | #848 |
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-intentionality · How It Works · Data refreshed daily, snapshot 2026-11-16.