IKEA-Bench (Visual+Text) - Next-Step Prediction: leaderboard
Metric: Accuracy (%) of next-step prediction (pick the diagram of the step after the one shown in video from four diagrams; 204 questions; chance 25) on IKEA-Bench, wordless IKEA manual diagrams against real assembly video from 29 products, Visual+Text setting (each diagram image followed by a text description of it), zero-shot greedy decoding, unparsed answers counted wrong; higher is better. Source: arxiv.org. Saturation forecast: Around 2029. 17 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.5 27B | 45.1 |
| 2 | Qwen 3.5 9B | 35.8 |
| 3 | Gemma 3 12B | 34.8 |
| 4 | Qwen 2.5 VL 7B | 33.8 |
| 5 | Qwen 3.5 2B | 33.8 |
| 6 | GLM-4.1V-9B (Thinking) | 32.8 |
| 7 | Gemma 3 27B | 30.4 |
| 8 | Gemma 3 4B | 27 |
Interactive version: theaggregate.ai/benchmark?slug=ikea-bench-visual-plustext-next-step-prediction · How It Works · Data refreshed daily, snapshot 2026-10-07.