GTO Wizard Benchmark
This provides researchers with a precise and quantifiable setting for evaluating planning and reasoning in multi-agent systems with partial observability, though it is incremental as it builds on existing poker benchmarks.
The authors tackled the problem of benchmarking algorithms in Heads-Up No-Limit Texas Hold'em by introducing GTO Wizard Benchmark, a public API and standardized evaluation framework that uses a superhuman AI agent to assess state-of-the-art large language models, revealing they all perform far below the benchmark's baseline.
We introduce GTO Wizard Benchmark, a public API and standardized evaluation framework for benchmarking algorithms in Heads-Up No-Limit Texas Hold'em (HUNL). The benchmark evaluates agents against GTO Wizard AI, a state-of-the-art superhuman poker agent that approximates Nash Equilibria, and defeated Slumbot, the 2018 Annual Computer Poker Competition champion and previous strongest publicly accessible HUNL benchmark, by $19.4$ $\pm$ $4.1$ bb/100. Variance is a fundamental challenge in poker evaluation; we address this by integrating AIVAT, a provably unbiased variance reduction technique that achieves equivalent statistical significance with ten times fewer hands than naive Monte Carlo evaluation. We conduct a comprehensive benchmarking study of state-of-the-art large language models under zero-shot conditions, including GPT-5.4, Claude Opus 4.6, Gemini 3.1 Pro, Grok 4, and others. Initial results and analysis reveal dramatic progress in LLM reasoning over recent years, yet all models remain far below the baseline established by our benchmark. Qualitative analysis reveals clear opportunities for improvement, including representation and the ability to reason over hidden states. This benchmark provides researchers with a precise and quantifiable setting to evaluate advances in planning and reasoning in multi-agent systems with partial observability.