PolyBench: Benchmarking LLM Forecasting and Trading Capabilities on Live Prediction Market Data

TL;DR

PolyBench is a comprehensive benchmark dataset and evaluation framework for testing large language models' ability to predict and trade on live prediction market data, integrating multimodal signals and financial metrics.

Contribution

It introduces PolyBench, a novel multimodal benchmark with real market data, and evaluates LLMs' forecasting and trading performance in a realistic setting.

Findings

Only two models achieved positive financial returns.

Models showed a gap between language fluency and probabilistic reasoning.

PolyBench provides a contamination-proof, financially-grounded evaluation standard.

Abstract

Predicting real-world events from live market signals demands systems that fuse qualitative news with quantitative order-book dynamics under strict temporal discipline -- a challenge existing benchmarks fail to capture. We present \textbf{PolyBench}, a multimodal benchmark derived from Polymarket that records point-in-time cross-sections of 38,666 binary prediction markets spanning 4,997 events, synchronously coupling each snapshot with a Central Limit Order Book (CLOB) state and a real-time news stream. Using PolyBench, we evaluate seven state-of-the-art Large Language Models -- spanning open- and closed-source families -- generating 36,165 predictions under identical, timestamp-locked market states collected between February 6 and 12, 2026. Our multidimensional framework assesses directional accuracy, our proposed Confidence-Weighted Return (CWR), Annualized Percentage Yield (APY), and Sharpe ratio via realistic order-book execution simulation. The results reveal a pronounced performance divergence: only two of seven models achieve positive financial returns -- MiMo-V2-Flash at \textbf{17.6%} CWR and Gemini-3-Flash at 6.2% CWR -- while the remaining five incur losses despite uniformly high stated confidence. These findings highlight the gap between surface-level language fluency and genuine probabilistic reasoning under live market uncertainty, and establish PolyBench as a contamination-proof, financially-grounded evaluation standard for future LLM research. Our dataset and code available at \underline{\href{https://github.com/PolyBench/PolyBench}{https://github.com/PolyBench/PolyBench}}.