CoreCognition Image + Video Mean: leaderboard
CoreCognition Image + Video Mean — 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) | 74.91 | #313 | |
| 2 | GPT-4o | 69.25 | #744 | |
| 3 | Qwen 2.5 VL 72B Instruct | 68.29 | #848 | |
| 4 | Qwen-VL-Max-2025-01-25 | 67.91 | ||
| 5 | Gemini 1.5 Pro | 67.8 | #1061 | |
| 6 | Gemini 1.5 Flash | 65.5 | #1694 | |
| 7 | GPT-4 Turbo | 65.23 | #999 | |
| 8 | Grok 2 (1212) | 63.69 | #1072 | |
| 9 | llava-video-72b-qwen2_multi_frame | CoreCognition run: native-setting=llava-video-72b-qwen2_multi_frame | 63.09 | |
| 10 | Gemini 1.5 Flash-8B | 62.91 | #2670 | |
| 11 | Qwen 2.5 VL 7B Instruct | 62.69 | #1867 | |
| 12 | Claude 3.5 Sonnet (20240620) | 61.92 | #692 | |
| 13 | Qwen-VL-Plus-2025-01-25 | 61.69 | ||
| 14 | Claude 3.7 Sonnet (20250219) | 61.44 | #414 | |
| 15 | DeepSeek-VL2-Small | 61.36 | #2401 |
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-mean · How It Works · Data refreshed daily, snapshot 2026-11-16.