# The Token Games: Evaluating Language Model Reasoning with Puzzle Duels

arXiv: https://arxiv.org/abs/2602.17831 · HTML: https://mlsanity.com/paper/2602.17831/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 22 of its 32 references that are in the map.
- First posted on arXiv 19 Feb 2026.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 22 of 22)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [STaR: Bootstrapping Reasoning With Reasoning](https://mlsanity.com/paper/2203.14465/) (2022)
- [Show Your Work: Scratchpads for Intermediate Computation with Language Models](https://mlsanity.com/paper/2112.00114/) (2021)
- [MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models](https://mlsanity.com/paper/2309.12284/) (2023)
- [Absolute Zero: Reinforced Self-play Reasoning with Zero Data](https://mlsanity.com/paper/2505.03335/) (2025)
- [FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI](https://mlsanity.com/paper/2411.04872/) (2024)
- [ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems](https://mlsanity.com/paper/2505.11831/) (2025)
- [SmartPlay: A Benchmark for LLMs as Intelligent Agents](https://mlsanity.com/paper/2310.01557/) (2023)
- [STP: Self-play LLM Theorem Provers with Iterative Conjecturing and Proving](https://mlsanity.com/paper/2502.00212/) (2025)
- [Learning Formal Mathematics From Intrinsic Motivation](https://mlsanity.com/paper/2407.00695/) (2024)
- [Copilot Arena: A Platform for Code LLM Evaluation in the Wild](https://mlsanity.com/paper/2502.09328/) (2025)
- [Programming Puzzles](https://mlsanity.com/paper/2106.05784/) (2021)
- [TextQuests: How Good are LLMs at Text-Based Video Games?](https://mlsanity.com/paper/2507.23701/) (2025)
- [PuzzlePlex: Benchmarking Foundation Models on Reasoning and Planning with Puzzles](https://mlsanity.com/paper/2510.06475/) (2025)

## Abstract (arXiv)

Evaluating the reasoning capabilities of Large Language Models is increasingly challenging as models improve. Human curation of hard questions is highly expensive, especially in recent benchmarks using PhD-level domain knowledge to challenge the most capable models. Even then, there is always a concern about whether these questions test genuine reasoning or if similar problems have been seen during training. Here, we take inspiration from 16th-century mathematical duels to design The Token Games (TTG): an evaluation framework where models challenge each other by creating their own puzzles. We leverage the format of Programming Puzzles - given a function that returns a boolean, find inputs that make it return True - to flexibly represent problems and enable verifying solutions. Using results from pairwise duels, we then compute Elo ratings, allowing us to compare models relative to each other. We evaluate 10 frontier models on TTG, and closely match the ranking from existing benchmarks such as Humanity's Last Exam, spending less than 200 USD and without involving any human effort in creating puzzles. We also find that creating good puzzles is still a highly challenging task for current models. Overall, our work suggests new paradigms for evaluating reasoning that avoid saturation by design, and that allow testing models for other skills like creativity and task creation alongside problem solving.