CFMME - Application QA: 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 questions about real financial document images; higher is better.
Metric: Accuracy (%) on question answering over real financial document images (application assessment) 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
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Qwen 3 VL 235B A22B (Thinking) | 54.94 | #459 | |
| 2 | Qwen 3 VL 235B A22B Instruct | 52.57 | #532 | |
| 3 | GLM-4.5V | Thinking | 51.35 | #754 |
| 4 | InternVL3.5-241B-A28B | Thinking | 50.08 | #733 |
| 5 | ERNIE 4.5 VL 28B A3B (Thinking) | 45.99 | ||
| 6 | Qwen 3 VL 8B (Thinking) | 44.22 | #910 | |
| 7 | Qwen 3 VL 8B Instruct | 43.8 | #1029 | |
| 8 | InternVL3.5-8B | Thinking | 43.29 | #1604 |
| 9 | ERNIE 4.5 VL 28B A3B | 42.07 | #2121 | |
| 10 | GLM-4.1V-9B (Thinking) | 41.81 | ||
| 11 | GPT-4o | 37.05 | #751 | |
| 12 | Kimi-VL-A3B (Thinking) | 36.37 | ||
| 13 | Kimi-VL-A3B-Instruct | 19.41 | #2253 | |
| 14 | Llama 3.2 11B Instruct | 18.61 | #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-application-qa · How It Works · Data refreshed daily, snapshot 2026-11-21.