{"repo":"HiThink-Research/FinMTM","free":true,"listed":false,"github":"https://github.com/HiThink-Research/FinMTM","clone":"git clone https://github.com/HiThink-Research/FinMTM.git","description":"FinMTM: A Multi-Turn Multimodal Benchmark for Financial Reasoning and Agent Evaluation","language":"Python","stars":31,"topics":["ai-benchmarking","ai-evaluation","benchmark","finance","financial-analysis","financial-llm"],"license":null,"category":"trading","readme_excerpt":"FinMTM: A Multi-Turn Multimodal Benchmark for Financial Reasoning and Agent Evaluation Chenxi Zhang 1,2 , Ziliang Gan 1,3 , Liyun Zhu 1 , Youwei Pang 4 , Qing Zhang 5 , Rongjunchen Zhang 1 ♠ 1 HiThink Research   2 Wuhan University   3 Zhejiang University   4 Nanyang Technological University   5 Shanghai Institute of Technology   Equal Contribution   ♠ Corresponding Author   Correspondence: zhangrongjunchen@myhexin.com 🤗 [Huggingface] Overview of FinMTM: task types and capability coverage. --- 🔥 Updates - 2026-07 : Evaluation code and documentation synchronized with the submitted manuscript. - 2026-01 : Initial release of benchmark dataset and paper. - TBD : Online leaderboard opens for submissions. --- 📌 Contents - Overview - Representative Examples - Results - Evaluation - Quickstart - License - Citation --- 🧭 Overview Financial reasoning is challenging for VLMs due to specialized chart formats, dense domain knowledge, long-horizon dependencies, and evidence-grounded tool use. Existing benchmarks are mostly single-turn and do not sufficiently measure multi-turn dialogue stability , session-level memory , or agentic planning and execution . FinMTM addresses this gap by providing: - Objective questions : single and multiple choice questions grounded in financial visuals. - Open-ended questions : multi-turn conversations that stress compositional reasoning, multi-step calculation, self-correction, and memory. - Financial agent task : tool-","default_branch":null,"files":null,"tree":[],"storefront":"/r/HiThink-Research","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/HiThink-Research/FinMTM/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}