Browse State-of-the-Art › Math Word Problem Solving

Math Word Problem Solving

80 papers with code · 13 benchmarks · 23 datasets archive 2025-07-28

Reasoning

A math word problem is a mathematical exercise (such as in a textbook, worksheet, or exam) where significant background information on the problem is presented in ordinary language rather than in mathematical notation. As most word problems involve a narrative of some sort, they are sometimes referred to as story problems and may vary in the amount of technical language used.

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

13 leaderboard tables shown for this task, 13 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 13 until expanded.

Syntology 74 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 1 placed): MATH (53 judged, 0 placed), SVAMP (18 judged, 0 placed), MAWPS (2 judged, 1 placed), ASDiv-A (1 judged, 0 placed), MathQA (4 judged, 0 placed), MATH minival (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
MATH (135 rows) Gemini 2.0 Flash Experimental — — — Compare
SVAMP (26 rows) GPT-4 (Teaching-Inspired) Teaching-Inspired Integrated Prompting Framework: A Novel Approach... code Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified Compare
MAWPS (25 rows) OpenMath-CodeLlama-70B (w/ code) OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset code — Compare
Math23K (19 rows) GPT-4 (Teaching-Inspired) Teaching-Inspired Integrated Prompting Framework: A Novel Approach... code Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified Compare
ALG514 (10 rows) MixedSP Learning from Explicit and Implicit Supervision Jointly For... — — Compare
ASDiv-A (9 rows) ATHENA (roberta-large) ATHENA: Mathematical Reasoning with Thought Expansion code — Compare
ParaMAWPS (6 rows) DeBERTa (VM) Math Word Problem Solving by Generating Linguistic Variants of... code — Compare
DRAW-1K (5 rows) EPT EPT-X: An Expression-Pointer Transformer model that generates... code — Compare
MathQA (5 rows) ELASTIC (RoBERTa-large) ELASTIC: Numerical Reasoning with Adaptive Symbolic Compiler code Syntology official (archive's flag): 2 ran · 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified Compare
SVAMP (1:N) (2 rows) ATHENA (roberta-large) ATHENA: Mathematical Reasoning with Thought Expansion code — Compare
GSM-Plus (1 row) GPT-4 GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness... code — Compare
MATH minival (1 row) Process Supervision (GPT-4) Let's Verify Step by Step code Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified Compare
PEN (1 row) EPT-X EPT-X: An Expression-Pointer Transformer model that generates... code — Compare

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

23 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Papers archive 2025-07-28

archive papers tagged: 107 · with a code link: 80 · where Syntology ran a sample: 39 (34 with a run with no instrument failure, 5 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (39 of 107 tagged: 34 with a run with no instrument failure, 5 where every run was a failure of Syntology's instrument)

Page 1 of 2: papers 1 to 100 of 107, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

Syntology lines on 41 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

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