CoreCognition Image + Video Mechanicalreasoning: leaderboard
CoreCognition Image + Video Mechanicalreasoning — 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 | Qwen-VL-Max-2025-01-25 | 86.2 | ||
| 2 | Qwen 2.5 VL 72B Instruct | 85.66 | #848 | |
| 3 | O1 (2024-12-17) | 85.13 | #313 | |
| 4 | Qwen 2 VL 72B Instruct | 81.81 | #1388 | |
| 5 | Gemini 1.5 Pro | 80.56 | #1061 | |
| 6 | InternVL2-76B | 78.85 | #1519 | |
| 7 | GPT-4o | 77.51 | #744 | |
| 8 | llava-video-72b-qwen2_multi_frame | CoreCognition run: native-setting=llava-video-72b-qwen2_multi_frame | 76.79 | |
| 9 | GPT-4 Turbo | 75.81 | #999 | |
| 10 | Gemini 1.5 Flash | 72.13 | #1694 | |
| 11 | Gemma 3 27B (IT) | 70.53 | #1322 | |
| 12 | Gemma 3 12B (IT) | 70.35 | #1884 | |
| 13 | LLaVA-NeXT-72B | 70.07 | #3185 | |
| 14 | InternVL2-4B | 69.89 | #4033 | |
| 15 | InternVL2-8B | 69.53 | #3186 |
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-mechanicalreasoning · How It Works · Data refreshed daily, snapshot 2026-11-16.