CFMME - Knowledge: 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 accuracy in percent on financial knowledge and certification exam questions with images; higher is better.

Metric: Accuracy (%) on the knowledge assessment (financial subject and professional certification exam questions with images) on CFMME (6,052 Chinese financial multimodal instances over eight financial image types), zero-shot, mean of three runs; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 14 models tracked. Updated 7 Oct 2026.

Top models

#ModelSettingScoreOverall rank
1Qwen 3 VL 235B A22B (Thinking)77.27#459
2Qwen 3 VL 235B A22B Instruct74.05#532
3GLM-4.5VThinking70.2#754
4InternVL3.5-241B-A28BThinking69.72#733
5Qwen 3 VL 8B (Thinking)63.47#910
6Qwen 3 VL 8B Instruct61.85#1029
7GLM-4.1V-9B (Thinking)61.21
8ERNIE 4.5 VL 28B A3B (Thinking)59.4
9InternVL3.5-8BThinking58.47#1604
10GPT-4o56.87#751
11ERNIE 4.5 VL 28B A3B49.28#2121
12Kimi-VL-A3B (Thinking)47.33
13Kimi-VL-A3B-Instruct36.52#2253
14Llama 3.2 11B Instruct21.79#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-knowledge · How It Works · Data refreshed daily, snapshot 2026-11-21.