Multi-domain Multi-modal Document Classificati: leaderboard
Document classification forms the backbone of modern enterprise content management, yet existing benchmarks remain trapped in oversimplified paradigms -- single domain settings with flat label structures -- that bear little resemblance to the hierarchical, multi-modal, and cross-domain nature of real-world business documents. This gap not only misrepresents practical complexity but also stifles pr
Metric: HF1 (self-reported). Source: benchmarklist.com. Saturation forecast: Around June 2027. 15 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 64.98 | #58 |
| 2 | Claude Opus 4.6 | 64.01 | #63 |
| 3 | Claude Opus 4.5 | 61.59 | #83 |
| 4 | Qwen 3.6 Plus | 58.26 | #120 |
| 5 | Kimi K2.5 | 57.06 | #144 |
| 6 | GPT-5.4 | 55.85 | #79 |
| 7 | GLM-5 | 54.67 | #141 |
| 8 | GPT-5.2 | 54.35 | #110 |
| 9 | Qwen 3.5 27B | 51.75 | #187 |
| 10 | MiniMax-M2.7 | 51.36 | #258 |
| 11 | Qwen 3 VL 235B A22B | 48.13 | #238 |
| 12 | Qwen 3.5 35B A3B | 45.38 | #256 |
| 13 | Qwen 3.5 9B | 38.69 | #379 |
| 14 | Qwen 2.5 VL 7B | 6.66 | #643 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=multi-domain-multi-modal-document-classificati · How It Works · Data refreshed daily, snapshot 2026-10-20.