Papers › MR-GSM8K: A Meta-Reasoning Benchmark for Large Language Model Evaluation

MR-GSM8K: A Meta-Reasoning Benchmark for Large Language Model Evaluation

28 Dec 2023arXiv:2312.17080archive 2025-07-28

Zhongshen Zeng, Pengguang Chen, Shu Liu, Haiyun Jiang, Jiaya Jia

In this work, we introduce a novel evaluation paradigm for Large Language Models (LLMs) that compels them to transition from a traditional question-answering role, akin to a student, to a solution-scoring role, akin to a teacher. This paradigm, focusing on "reasoning about reasoning," hence termed meta-reasoning, shifts the emphasis from result-oriented assessments, which often neglect the reasoning process, to a more comprehensive evaluation that effectively distinguishes between the cognitive capabilities of different models. By applying this paradigm in the GSM8K dataset, we have developed the MR-GSM8K benchmark. Our extensive analysis includes several state-of-the-art models from both open-source and commercial domains, uncovering fundamental deficiencies in their training and evaluation methodologies. Notably, while models like Deepseek-v2 and Claude3-Sonnet closely competed with GPT-4 in GSM8K, their performance disparities expanded dramatically in MR-GSM8K, with differences widening to over 20 absolute points, underscoring the significant challenge posed by our meta-reasoning approach.

PaperPDFCode

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

Code

dvlab-research/diaggsm8k officialmentioned in papermentioned on GitHubpytorch report
dvlab-research/mr-gsm8k officialmentioned in papermentioned on GitHubpytorch 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

GSM8KLanguage Model EvaluationLanguage ModelingLanguage ModellingLarge Language ModelMathQuestion Answering

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutFocusGPT-4Label SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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