Game of 24

Four-number puzzles that must equal 24; OpenCompass runs a five-puzzle Tree-of-Thoughts slice of the Princeton Game-of-24 set.

Also known as: game-of-24, ToT Game of 24, Game24

unassessed

This page is a discovery lead. Nobody has yet assessed it against the catalogue contract, so it carries no disposition. Absence of evidence here is not evidence of staleness.
Categorymath
Subcategoryfour-number arithmetic puzzles scored by exact use of each number to make 24
Page statusactive
Metricaccuracy (share of puzzles whose expression uses the four numbers once and equals 24)
Directionhigher_is_better
Unit%
Dataset size5
Dataset licenceMIT (Hugging Face card, ToT repository, and ToT LICENSE, Copyright 2023 Shunyu Yao); OpenCompass Apache-2.0
PublisherPrinceton NLP (ToT paper and original task); OpenCompass (harness config)

What it measures

Game of 24 is a grade-school puzzle: given four integers, use each exactly once with +, -, *, / to make 24. Yao et al. 2023 (Tree of Thoughts) scrape 1,362 ranked games from 4nums.com and test the hard band indexed 901–1000. Success is a valid expression that equals 24 and uses the four inputs once each. OpenCompass dataset Game24Dataset loads Hugging Face test-time-compute/game-of-24 (or a local CSV) and then slices `data[900:905]`, i.e. five puzzles, not the paper's 100. The OpenCompass config uses ToTInferencer (propose / value / greedy, n_evaluate_sample=3, n_select_sample=5), matching the paper's Game-of-24 ToT setup.

Task format

OpenCompass generation with a Tree-of-Thoughts inferencer and Game24PromptWrapper (standard, chain-of-thought, and propose/value prompts copied from the ToT repo). ZeroRetriever. Game24Evaluator checks the extracted expression with sympy and a digit-multiset check. Temperature 0.7 in game24_gen_52a460.py with do_sample=False.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub