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

#ModelSettingScoreOverall rank
1Qwen 3 VL 235B A22B Instruct88.27#532
2GPT-4o81.45#751
3Qwen 3 VL 8B Instruct79.15#1029
4GLM-4.5VNon-reasoning77.25#754
5ERNIE 4.5 VL 28B A3B73.86#2121
6InternVL3.5-8BNon-reasoning65.7#1604
7InternVL3.5-241B-A28BNon-reasoning60.25#733
8Kimi-VL-A3B-Instruct50.86#2253
9Llama 3.2 11B Instruct13.44#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.