CoreCognition Image only Mechanicalreasoning: leaderboard
CoreCognition Image only 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: Rough model projection: around 2026. 77 models tracked. Updated 16 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | NVLM-D-72B | 77.08 | #2181 |
| 2 | Ovis1.6-Gemma2-27B | 74.62 | #1833 |
| 3 | Step-1.5V-mini | 74.15 | #2720 |
| 4 | step-1o-turbo-vision | 73.96 | |
| 5 | Molmo-72B-0924 | 72.35 | #5272 |
| 6 | 360VL-70B | 69.79 | #5987 |
| 7 | GLM-4V-Plus | 66.57 | #1400 |
| 8 | step-1v-32k | 60.32 | |
| 9 | Cambrian-34B | 59.47 | #5295 |
| 10 | wemm-chat-2k-cn | 57.77 | |
| 11 | wemm-chat-cn | 57.67 | |
| 12 | Reka Core | 57.58 | #3349 |
| 13 | GLM-4V-9B | 57.39 | #3333 |
| 14 | WeMM | 56.44 | #5473 |
| 15 | omchat | 55.97 |
Interactive version: theaggregate.ai/benchmark?slug=corecognition-image-only-mechanicalreasoning · How It Works · Data refreshed daily, snapshot 2026-11-16.