FinMTM: A Multi-Turn Multimodal Benchmark for Financial Reasoning and Agent Evaluation
This provides a more realistic evaluation tool for financial AI applications, though it is incremental as it builds on existing benchmark concepts.
The authors tackled the lack of comprehensive benchmarks for evaluating vision-language models in finance by introducing FinMTM, a multi-turn multimodal benchmark with 11,133 bilingual QA pairs, which revealed limitations in existing models across various tasks.
The financial domain poses substantial challenges for vision-language models (VLMs) due to specialized chart formats and knowledge-intensive reasoning requirements. However, existing financial benchmarks are largely single-turn and rely on a narrow set of question formats, limiting comprehensive evaluation in realistic application scenarios. To address this gap, we propose FinMTM, a multi-turn multimodal benchmark that expands diversity along both data and task dimensions. On the data side, we curate and annotate 11{,}133 bilingual (Chinese and English) financial QA pairs grounded in financial visuals, including candlestick charts, statistical plots, and report figures. On the task side, FinMTM covers single- and multiple-choice questions, multi-turn open-ended dialogues, and agent-based tasks. We further design task-specific evaluation protocols, including a set-overlap scoring rule for multiple-choice questions, a weighted combination of turn-level and session-level scores for multi-turn dialogues, and a composite metric that integrates planning quality with final outcomes for agent tasks. Extensive experimental evaluation of 22 VLMs reveal their limitations in fine-grained visual perception, long-context reasoning, and complex agent workflows.