CFMME - Seal Detection: leaderboard
Metric: Seal detection mAP (%): boxes and categories (company or personal seal) on 756 document images on CFMME (6,052 Chinese financial multimodal instances over eight financial image types), zero-shot, mean of three runs, the non-reasoning model of each family; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GLM-4.5V (Non-reasoning) | 37.45 |
| 2 | Qwen 3 VL 235B A22B Instruct | 30.27 |
| 3 | Qwen 3 VL 8B Instruct | 28.27 |
| 4 | GPT-4o | 0.3 |
| 5 | Llama 3.2 11B Instruct | 0 |
| 6 | ERNIE 4.5 VL 28B A3B | 0 |
Interactive version: theaggregate.ai/benchmark?slug=cfmme-seal-detection · How It Works · Data refreshed daily, snapshot 2026-10-07.