MMM-Bench - Level 4 (Business Form): leaderboard
MMM-Bench (2026, Alibaba) zero-shot document classification at taxonomy level 4, Business Form, for real enterprise documents classified using the paper’s hierarchical category prompt. Macro-F1 in percent; higher is better.
Metric: Macro-F1 (%) at taxonomy level 4 (Business Form), zero-shot hierarchical classification of the test split (20 percent of 5,990 real Alibaba business documents in 12 domains, mostly Chinese) with a document prompt containing OCR text, image-page placeholders and optional filename; actual image-tensor input is described only for multimodal implementations against a flattened five-level taxonomy, temperature 0.1; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 15 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 80.14 | #102 |
| 2 | Claude Opus 4.5 | 77.13 | #165 |
| 3 | GPT-5.4 | 75.1 | #138 |
| 4 | Claude Opus 4.6 | 71.4 | #114 |
| 5 | GPT-5.2 | 68.16 | #190 |
| 6 | Qwen 3.6 Plus | 63.96 | #245 |
| 7 | Qwen 3.5 27B | 57.74 | #380 |
| 8 | Qwen 3 VL 235B A22B | 57.53 | #486 |
| 9 | GLM-5 | 56.23 | #276 |
| 10 | Kimi K2.5 | 53.27 | #272 |
| 11 | Qwen 3.5 35B A3B | 51.89 | #494 |
| 12 | MiniMax-M2.7 | 48.62 | #539 |
| 13 | Qwen 3.5 9B | 38.82 | #838 |
| 14 | Qwen 3 VL 8B | 14.51 | #927 |
| 15 | Qwen 2.5 VL 7B | 0 | #1878 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=mmm-bench-level-4-business-form · How It Works · Data refreshed daily, snapshot 2026-11-22.