Papers › TinyGSM: achieving >80% on GSM8k with small language models

TinyGSM: achieving >80% on GSM8k with small language models

14 Dec 2023arXiv:2312.09241archive 2025-07-28

Bingbin Liu, Sebastien Bubeck, Ronen Eldan, Janardhan Kulkarni, Yuanzhi Li, Anh Nguyen, Rachel Ward, Yi Zhang

Small-scale models offer various computational advantages, and yet to which extent size is critical for problem-solving abilities remains an open question. Specifically for solving grade school math, the smallest model size so far required to break the 80% barrier on the GSM8K benchmark remains to be 34B. Our work studies how high-quality datasets may be the key for small language models to acquire mathematical reasoning. We introduce \texttt{TinyGSM}, a synthetic dataset of 12.3M grade school math problems paired with Python solutions, generated fully by GPT-3.5. After finetuning on \texttt{TinyGSM}, we find that a duo of a 1.3B generation model and a 1.3B verifier model can achieve 81.5% accuracy, outperforming existing models that are orders of magnitude larger. This also rivals the performance of the GPT-3.5 ``teacher'' model (77.4%), from which our model's training data is generated. Our approach is simple and has two key components: 1) the high-quality dataset \texttt{TinyGSM}, 2) the use of a verifier, which selects the final outputs from multiple candidate generations.

PaperPDF

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Arithmetic ReasoningGSM8KMathMathematical Reasoning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Arithmetic Reasoning GSM8K Phi-GSM+V 1.3B+1.3B (verify48@1) Accuracy 81.5 #65 of 164 Archive leaderboard report
Arithmetic Reasoning GSM8K Phi-GSM+V 1.3B+1.3B (verify48@1) Parameters (Billion) 2.6 #65 of 164 Archive leaderboard report
Arithmetic Reasoning GSM8K Phi-GSM 2.7B (fine-tuned) Accuracy 74.3 #89 of 164 Archive leaderboard report
Arithmetic Reasoning GSM8K Phi-GSM 2.7B (fine-tuned) Parameters (Billion) 2.7 #89 of 164 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AdamAttentionAttention DropoutBPECosine AnnealingDense ConnectionsDropoutGPT-3Layer NormalizationLinear LayerLinear Warmup With Cosine AnnealingMulti-Head AttentionResidual ConnectionSoftmaxWeight 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