CFMME - Information Extraction: leaderboard
Metric: Field-level F1 (%) of key information extracted from financial documents 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: Estimated already saturated. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3 VL 235B A22B Instruct | 93.43 |
| 2 | GLM-4.5V (Non-reasoning) | 89.03 |
| 3 | Qwen 3 VL 8B Instruct | 88.86 |
| 4 | ERNIE 4.5 VL 28B A3B | 80.71 |
| 5 | GPT-4o | 66.88 |
| 6 | Llama 3.2 11B Instruct | 47.52 |
Interactive version: theaggregate.ai/benchmark?slug=cfmme-information-extraction · How It Works · Data refreshed daily, snapshot 2026-10-07.