CoreCognition Image + Video Perceptualconstancy: leaderboard
CoreCognition Image + Video Perceptualconstancy — 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) | 87.79 | #313 | |
| 2 | Qwen 2.5 VL 72B Instruct | 85.27 | #848 | |
| 3 | Qwen-VL-Max-2025-01-25 | 84.33 | ||
| 4 | GPT-4 Turbo | 82.17 | #999 | |
| 5 | GPT-4o | 81.2 | #744 | |
| 6 | Qwen 2 VL 72B Instruct | 80.81 | #1388 | |
| 7 | Gemini 1.5 Flash | 77.62 | #1694 | |
| 8 | XGen-MM-Instruct-Interleave-v1.5 | 77.33 | #7042 | |
| 9 | XGen-MM-Instruct-DPO-v1.5 | 77.13 | #7079 | |
| 10 | Claude 3.5 Sonnet (20240620) | 76.74 | #692 | |
| 11 | Claude 3 Opus (20240229) | 76.55 | #1125 | |
| 12 | llava-video-7b-qwen2_multi_frame | CoreCognition run: native-setting=llava-video-7b-qwen2_multi_frame | 76.16 | |
| 13 | Gemini 1.5 Flash-8B | 75.97 | #2670 | |
| 14 | Claude 3.7 Sonnet (20250219) | 75 | #414 | |
| 15 | DeepSeek-VL2-Small | 75 | #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-perceptualconstancy · How It Works · Data refreshed daily, snapshot 2026-11-16.