AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

FinMMR: Make Financial Numerical Reasoning More Multimodal, Comprehensive, and Challenging

Zichen Tang, Haihong E, Jiacheng Liu, Zhongjun Yang, Rongjin Li, Zihua Rong, Haoyang He, Zhuodi Hao, Xinyang Hu, Kun Ji, Ziyan Ma, Mengyuan Ji and 9 more

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Multimodal LLM benchmarks

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
enable 64K extended thinking (ablation)Claude 3.7 Sonnet · FinMMR test Hard (CoT)accuracy (%): 50.80 -> 53.00Improved
enable 64K extended thinking (token cost) (ablation)Claude 3.7 Sonnet · FinMMR test Hard tokenstokens (M): 0.34M -> 4.06MHurt
use PoT prompting instead of CoT (mean over models excluding QVQ) (ablation)MLLMs · FinMMR test Hardaccuracy (%): 36.20 -> 37.64Improved
use PoT instead of CoT (ablation)Qwen2.5-VL-72B · FinMMR test Mediumaccuracy (%): 63.42 -> 64.17Improved
use PoT instead of CoT (ablation)QVQ-72B-Preview · FinMMR test Hardaccuracy (%): 40.30 -> 6.20Hurt
use PoT instead of CoT (ablation)GPT-4o · FinMMR test Hardaccuracy (%): 45.40 -> 47.80Improved
add distractor images to ground images (ablation)Qwen2.5-VL-72B · FinMMR Medium validation (PoT)accuracy (%): 77.78 -> 64.73Hurt
add distractor images to ground images (ablation)Qwen2.5-VL-72B · FinMMR test Hard (PoT)accuracy (%): 57.18 -> 47.23Hurt
add visual filtering stage before reasoning (ablation)Qwen2.5-VL-72B · FinMMR Medium validation (PoT, distractors)accuracy (%): 64.73 -> 71.56Improved
add MLLM-instructed knowledge retrieval and judging (financial function library) (ablation)Gemini 2.0 Flash Thinking · FinMMR tabular QA (1,160 instances, PoT)accuracy (%): 78.71 -> 83.02Improved
add knowledge augmentation (ablation)GPT-4o · FinMMR tabular QA (1,160 instances, PoT)accuracy (%): 80.60 -> 83.62Improved
add knowledge augmentation (ablation)Claude 3.7 Sonnet (64K thinking) · FinMMR tabular QA (1,160 instances, PoT)accuracy (%): 83.53 -> 86.29Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy