SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.00344 · 2024

Can LLMs Master Math? Investigating Large Language Models on Math Stack Exchange

arXiv · PDF · Open in the Atlas

Code that ran

1 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 3 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2404.00344.json · badge: /api/ran/2404.00344.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
gipplab/llm-investig-mathstackexchange canonical (classifier label)
classifier basis: census
1 ran · 3 no recorded run
FunctionStatusWhere it lives
open_special_index Ran
ran; our contract draft was wrong, not the code
gipplab/llm-investig-mathstackexchange/code/pya0_replace/utils/collection_driver.py
code served (permissive licence) · get_code("f875ec2c8d261374")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import os
import pickle
import tempfile

# Create temporary directories for test cases
temp_dir = tempfile.mkdtemp()

# Test case 1: 'tcp' type (doesn't need file I/O)
tcp_arg = "tcp:localhost:9999"

# Test case 2: 'doclist' type (needs doclist.pkl file)
doclist_dir = os.path.join(temp_dir, "doclist_test")
os.makedirs(doclist_dir, exist_ok=True)
sample_doclist = [{"doc_id": 1, "content": "test"}, {"doc_id": 2, "content": "data"}]
with open(os.path.join(doclist_dir, "doclist.pkl"), "wb") as f:
    pickle.dump(sample_doclist, f)
doclist_arg = f"doclist:{doclist_dir}"

# Test case 3: 'docdict' type (needs docdict.pkl file)
docdict_dir = os.path.join(temp_dir, "docdict_test")
os.makedirs(docdict_dir, exist_ok=True)
sample_docdict = {"1": {"content": "test"}, "2": {"content": "data"}}
with open(os.path.join(docdict_dir, "docdict.pkl"), "wb") as f:
    pickle.dump(sample_docdict, f)
docdict_arg = f"docdict:{docdict_dir}"

# Build ARGS with one valid test case (using tcp since it's simplest)
ARGS = {
    "index_arg": tcp_arg
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
corpus_reader__arqmath3_rawxml Not yet run
unverified (harvested, no recorded run)
gipplab/llm-investig-mathstackexchange/code/genArqmathEmbeddings.py
code served (permissive licence) · get_code("9dd495c1023e73ea")
How it ran

no invocation recorded.

indexer__docid_vec_hnsw_faiss Not yet run
unverified (harvested, no recorded run)
gipplab/llm-investig-mathstackexchange/code/genArqmathEmbeddings.py
code served (permissive licence) · get_code("27f9429b0296bb98")
How it ran

no invocation recorded.

psg_encoder__llm Not yet run
unverified (harvested, no recorded run)
gipplab/llm-investig-mathstackexchange/code/genArqmathEmbeddings.py
code served (permissive licence) · get_code("63477d6d99ea46bf")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 4 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Large Language Models (LLMs) have demonstrated exceptional capabilities in various natural language tasks, often achieving performances that surpass those of humans. Despite these advancements, the domain of mathematics presents a distinctive challenge, primarily due to its specialized structure and the precision it demands. In this study, we adopted a two-step approach for investigating the proficiency of LLMs in answering mathematical questions. First, we employ the most effective LLMs, as identified by their performance on math question-answer benchmarks, to generate answers to 78 questions from the Math Stack Exchange (MSE). Second, a case analysis is conducted on the LLM that showed the highest performance, focusing on the quality and accuracy of its answers through manual evaluation. We found that GPT-4 performs best (nDCG of 0.48 and P@10 of 0.37) amongst existing LLMs fine-tuned for answering mathematics questions and outperforms the current best approach on ArqMATH3 Task1, considering P@10. Our Case analysis indicates that while the GPT-4 can generate relevant responses in certain instances, it does not consistently answer all questions accurately. This paper explores the current limitations of LLMs in navigating complex mathematical problem-solving. Through case analysis, we shed light on the gaps in LLM capabilities within mathematics, thereby setting the stage for future research and advancements in AI-driven mathematical reasoning. We make our code and findings publicly available for research: \url{https://github.com/gipplab/LLM-Investig-MathStackExchange}

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2404.00344")
get_code_for_paper("2404.00344")
have("2404.00344")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2404.00344.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2404.00344.svg)](https://syntology.ai/paper/2404.00344)

Connect an agent — have() is free.