GSM8K B
AI benchmark · Math
What is GSM8K?
GSM8K measures language models' multi-step mathematical reasoning on 8.5K grade school math word problems.
Math mostly
“we introduce GSM8K, a dataset of 8.5K high quality linguistically diverse grade school math word problems.”
arxiv.org/abs/2110.14168 ↗
Paper: arxiv.org/abs/2110.14168 ↗
Lineage
Benchmarks this one is built on and built from: versions, subsets, extensions and the indexes that combine them.
Derived benchmarks
GSM-SEM extension
“Benchmarks like GSM8K are popular measures of mathematical reasoning, but leaderboard gains can overstate true capability due to memorization of fixed test sets.”
arxiv.org/abs/2605.07053v2 ↗HELM GSM8K extension
“HELM GSM8K scores language models on grade school math word problems within Stanford CRFM's HELM evaluation framework.”
Multilingual MGSM extension
“MGSM measures language models' chain-of-thought math reasoning on 250 grade-school math problems manually translated from GSM8K into ten typologically diverse languages.”
Included in
OMLAB Open Agent Math Leaderboard
“A leaderboard that compares prompting and agent algorithms (IO, CoT, SC-CoT, PoT, ReAct, ToT) across LLMs on math datasets GSM8K, AQuA and MATH-500, reporting score and cost.”
Tier B
Established: 15 or more models scored, or curated RL directories rate it.
How much stands behind a tier: usage, who backs it, a confirmed line from its own site or paper, and a clear read on X. High with three of the four, medium with two, low otherwise.
- 23 models scored
- in curated RL directories (2 pts)
On X · mixed, moderate buzz, from 11 posts about GSM8K in the last month
GSM8K is still widely used as a sanity check in research, quantization and serving posts, but frontier scores near 97% show it is saturated.
How we got to tier B
- Adoption: 23 models scored. Tier B.
- On X: mixed, moderate buzz. “GSM8K is still widely used as a sanity check in research, quantization and serving posts, but frontier scores near 97% show it is saturated.” No move.
- In curated RL directories: 2 points, a floor of C.
- Confirmed: a line from its own site or paper places it.
A clear view on X moves a tier one step up or down; most entries don't move. How tiers work.
Where GSM8K sits
Its domain on the map, live. Hover a logo for its name; click to open it. Open it on the full map
Next: browse all benchmarks. Entry from the RL Research daily scrape of public sources, 2026-11-05 snapshot.