IndustryBench-MIPU - Single-Image: leaderboard
IndustryBench-MIPU (2026) single-image extraction: each industrial product image is processed on its own and the extracted property-value pairs are scored against image-level annotations. F1 in percent; higher is better.
Metric: Image-level F1 (%) of single-image extraction (each image processed independently), 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: Not forecast. 9 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3.5 Plus (Thinking) | 81.3 | #232 (Qwen 3.5 Plus) |
| 2 | Gemini 3.1 Pro (Preview) | 77.1 | #94 |
| 3 | Qwen 3.5 397B A17B | 76 | #246 |
| 4 | Qwen 3.5 27B | 71.5 | #359 |
| 5 | Kimi K2.5 (Thinking) | 70.9 | #256 (Kimi K2.5) |
| 6 | Qwen 3.5 122B A10B | 70.5 | #331 |
| 7 | Claude Opus 4.6 (Thinking) | 69.4 | #102 (Claude Opus 4.6) |
| 8 | Qwen 3.5 35B A3B | 68.7 | #482 |
| 9 | GPT-5.4 (Thinking) | 66.2 | #123 (GPT-5.4) |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=industrybench-mipu-single-image · How It Works · Data refreshed daily, snapshot 2026-11-13.