FinTradeBench: A Financial Reasoning Benchmark for LLMs

arXiv:2603.19225 · cs.CE, cs.AI, cs.CL, cs.IR, q-fin.CP · Submitted 2026-03-19 · Read on arXiv

cs.CE, cs.AI, cs.CL, cs.IR, q-fin.CP

Submitted: 2026-03-19

Updated: 2026-10-13

Terminology

• Benchmark — 4× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Calibration — 1× in this paper · explained in 7 episodes
• LLM judge — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes

Sources

• FinBERT: Financial Sentiment Analysis with Pre-trained Language Models
• Training Verifiers to Solve Math Word Problems
• Exploring Large Language Models for Financial Applications: Techniques, Performance, and Challenges with FinMA
• RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systems
• Retrieval-Augmented Generation for Large Language Models: A Survey
• FinanceBench: A New Benchmark for Financial Question Answering
• Volatility Forecasting in Global Financial Markets Using TimeMixer
• Profit Mirage: Revisiting Information Leakage in LLM-based Financial Agents
• Holistic Evaluation of Language Models
• BizFinBench: A Business-Driven Real-World Financial Benchmark for Evaluating LLMs
• FinToolBench: Evaluating LLM Agents for Real-World Financial Tool Use
• A Systematic Investigation of Document Chunking Strategies and Embedding Sensitivity
• Reflexion: Language Agents with Verbal Reinforcement Learning
• FinChart-Bench: Benchmarking Financial Chart Comprehension in Vision-Language Models
• Data-Efficient Realized Volatility Forecasting with Vision Transformers
• BloombergGPT: A Large Language Model for Finance
• Signed representing measures (Berger-type charges) in subnormality and related properties of weighted shifts
• FinGPT: Open-Source Financial Large Language Models
• InvestLM: A Large Language Model for Investment using Financial Domain Instruction Tuning
• Self-Rewarding Language Models

Related papers

• Constrained Sensing and Reliable State Estimation with Shallow Recurrent Decoders on a TRIGA Mark II Reactor
• A finite-element-inspired bipartite graph learned simulator for manufacturability assessment in large-deformation sheet forming
• Non-linear mechanical field reconstruction coupling recurrent neural networks with physics-informed graph neural networks
• Neural-Parameterized Cellular Automata for Wildfire Spread
• A mesh-based neural energy method for the simulation of heterogeneous composites
• Evidence-Unit Fairness and the Limits of Query-Adaptive Sparse-Dense Fusion in Financial Document Retrieval