Papers › Show, Don't Tell: Evaluating Large Language Models Beyond Textual Understanding with ChildPlay

Show, Don't Tell: Evaluating Large Language Models Beyond Textual Understanding with ChildPlay

12 Jul 2024arXiv:2407.11068archive 2025-07-28

Gonçalo Hora de Carvalho, Oscar Knap, Robert Pollice

We develop a systematic benchmark set to test the generalization of state-of-the-art large language models on broader problems beyond linguistic tasks and evaluate it on a systematic progression of GPT models (GPT-3.5, GPT-4, GPT-4o, GPT-4o-mini). Using well-known simple games like Tic-Tac-Toe, Connect Four, and Battleship, all encoded in ASCII, we test their strategic capabilities and spatial reasoning. To probe generalization, we introduce three new games: LEGO Connect Language (LCL) for spatial logic, a shape recognition game, and Guess-the-SMILES (GtS), an advanced spatial logic benchmark in chemistry. Results show that, despite proficiency in standard benchmarks, GPT models perform poorly in these games, failing to anticipate losing moves, play correctly, or recognize spatial relationships. Except for Tic-Tac-Toe and GtS, a systematic progression in gameplay performance as models are formally improved (GPT-3.5, GPT-4, GPT-4o) is not observed. GPT-4 succeeds in shape recognition, but all models consistently struggle with LCL and GtS. This suggests that while GPT models can emulate conversational proficiency and basic rule comprehension, they have limited cognitive flexibility and generalization in strategy and spatial reasoning. Our findings, highlighted with our benchmark suite (ChildPlay GitHub Repository), caution against claims of emergent intelligence in GPT models, which appear more specialized than general.

PaperPDFCode

Code

child-play-neurips/child-play officialmentioned in paper report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Spatial Reasoning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionAttention DropoutBPECosine AnnealingDense ConnectionsDiscriminative Fine-TuningDropoutGPTGPT-3GPT-4Label SmoothingLayer NormalizationLinear LayerLinear Warmup With Cosine AnnealingMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSETSoftmaxTransformerWeight Decay

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections