IndustryBench-MIPU: leaderboard
Metric: Product-level F1 (%) of multi-image extraction (the model receives all valid images of a product and outputs product-level property-value pairs), structured attribute value extraction from industrial product images (specification tables, nameplates, technical drawings): property names matched exactly and values by rule-based normalization then a Qwen 3.6 Plus semantic judge; full extraction prompt, thinking enabled where supported; higher is better. Source: arxiv.org. Saturation forecast: Around December 2026. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 65.1 |
| 2 | Qwen 3.5 397B A17B | 62.7 |
| 3 | GPT-5.4 (Thinking) | 60.5 |
| 4 | Qwen 3.5 Plus (Thinking) | 59.9 |
| 5 | Claude Opus 4.6 (Thinking) | 57.2 |
| 6 | Kimi K2.5 (Thinking) | 56.7 |
| 7 | Qwen 3.5 27B | 55.8 |
| 8 | Qwen 3.5 122B A10B | 50.1 |
| 9 | Qwen 3.5 35B A3B | 20.6 |
Interactive version: theaggregate.ai/benchmark?slug=industrybench-mipu · How It Works · Data refreshed daily, snapshot 2026-09-29.