CFMME - Seal Recognition: leaderboard
CFMME (2026) is a Chinese financial multimodal evaluation set for vision-language models, built from financial documents, charts, seals, tables and exam questions. This board is the seal text recognition score in percent, one minus normalized edit distance; higher is better.
Metric: Seal text recognition score (%, 1 minus normalized edit distance) 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 February 2027. 9 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Qwen 3 VL 235B A22B Instruct | 88.27 | #532 | |
| 2 | GPT-4o | 81.45 | #751 | |
| 3 | Qwen 3 VL 8B Instruct | 79.15 | #1029 | |
| 4 | GLM-4.5V | Non-reasoning | 77.25 | #754 |
| 5 | ERNIE 4.5 VL 28B A3B | 73.86 | #2121 | |
| 6 | InternVL3.5-8B | Non-reasoning | 65.7 | #1604 |
| 7 | InternVL3.5-241B-A28B | Non-reasoning | 60.25 | #733 |
| 8 | Kimi-VL-A3B-Instruct | 50.86 | #2253 | |
| 9 | Llama 3.2 11B Instruct | 13.44 | #5174 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=cfmme-seal-recognition · How It Works · Data refreshed daily, snapshot 2026-11-21.