MMM-Bench - Level 1 (Business Function): leaderboard
Metric: Macro-F1 (%) at taxonomy level 1 (Business Function), zero-shot hierarchical classification of the test split (20 percent of 5,990 real Alibaba business documents in 12 domains, mostly Chinese) from OCR text, page images and filename against a flattened five-level taxonomy, temperature 0.1; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 15 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 86.1 |
| 2 | GPT-5.4 | 85.98 |
| 3 | Qwen 3 VL 235B A22B | 85 |
| 4 | Claude Opus 4.5 | 84.39 |
| 5 | Claude Opus 4.6 | 84.07 |
| 6 | Kimi K2.5 | 84.04 |
| 7 | GPT-5.2 | 83.27 |
| 8 | Qwen 3.6 Plus | 82.32 |
| 9 | Qwen 3.5 27B | 82.18 |
| 10 | MiniMax-M2.7 | 81.3 |
| 11 | Qwen 3.5 35B A3B | 80.33 |
| 12 | Qwen 3.5 9B | 79.8 |
| 13 | GLM-5 | 77.81 |
| 14 | Qwen 2.5 VL 7B | 47.03 |
Interactive version: theaggregate.ai/benchmark?slug=mmm-bench-level-1-business-function · How It Works · Data refreshed daily, snapshot 2026-10-07.