Papers › MathArena: Evaluating LLMs on Uncontaminated Math Competitions

MathArena: Evaluating LLMs on Uncontaminated Math Competitions

29 May 2025arXiv:2505.23281archive 2025-07-28

Mislav Balunović, Jasper Dekoninck, Ivo Petrov, Nikola Jovanović, Martin Vechev

The rapid advancement of reasoning capabilities in large language models (LLMs) has led to notable improvements on mathematical benchmarks. However, many of the most commonly used evaluation datasets (e.g., AIME 2024) are widely available online, making it difficult to disentangle genuine reasoning from potential memorization. Furthermore, these benchmarks do not evaluate proof-writing capabilities, which are crucial for many mathematical tasks. To address this, we introduce MathArena, a new benchmark based on the following key insight: recurring math competitions provide a stream of high-quality, challenging problems that can be used for real-time evaluation of LLMs. By evaluating models as soon as new problems are released, we effectively eliminate the risk of contamination. Using this framework, we find strong signs of contamination in AIME 2024. Nonetheless, evaluations on harder competitions, such as SMT 2025 -- published well after model release dates -- demonstrate impressive reasoning capabilities in top-performing models. MathArena is also the first benchmark for proof-writing capabilities. On USAMO 2025, even top models score below 25%, far behind their performance on final-answer tasks. So far, we have evaluated 30 models across five competitions, totaling 149 problems. As an evolving benchmark, MathArena will continue to track the progress of LLMs on newly released competitions, ensuring rigorous and up-to-date evaluation of mathematical reasoning.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 19 code samples harvested from 1 repository linked to this paper: 15 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 19 samples from 1 repository, 15 ran (13 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-25 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

eth-sri/matharena officialmentioned in paperMITSyntology: 19 samples, 15 ran (2 instrument-failed) · 4 unverified 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

19 samples harvested: 15 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · our draft was wrong
13ran
4unverified

Licence: 0 of the 19 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from eth-sri/matharena. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

eth-sri/matharena official repository 19 samples, 15 ran (2 instrument-failed) · 4 unverified
check_number_proximity_any_order src/matharena/grader.py ran MIT (permissive) · cebd63ce42db8cf0 · report fixture: signature gold:str/0/str, model:str/0/str, threshold:int/0/int · returned bool · level recorded 2026-09-25
exclude_configs src/matharena/configs.py ran MIT (permissive) · 3c24b8cb7ab88e6d · report fixture: signature configs:dict/0/?, human_readable_ids:dict/0/?, exclude_file_path:str/0/str, comp:str/0/str · returned tuple · level recorded 2026-09-25
extract_numbers in 14 papers src/matharena/grader.py ran MIT (permissive) · 811a3d879ce72f27 · report fixture: signature text:str/0/str · returned list · level recorded 2026-09-25
find_last_boxed_content src/matharena/parser.py ran MIT (permissive) · d8d2c5ba39e34d5f · report fixture: signature text:str/0/str, list_answer:bool/0/bool · returned tuple · level recorded 2026-09-25
load_configs src/matharena/configs.py ran fingerprinted MIT (permissive) · 19d49ff9409d85f2 · report fixture: signature root_dir:str/0/str, remove_extension:bool/0/bool · returned dict · level recorded 2026-09-25
load_json_zst src/matharena/json_zst.py ran MIT (permissive) · b8de5523615a315e · report fixture: signature path:PosixPath/0/? · returned dict · level recorded 2026-09-25
load_metadata in 23 papers src/matharena/arxivbench_utils.py ran MIT (permissive) · d2318c1b39c8b47e · report fixture: signature paper_root:str/0/str, paper_id:str/0/str · returned dict · level recorded 2026-09-25
load_model_config in 8 papers src/matharena/arxivbench_utils.py ran MIT (permissive) · 1556226ccd07a184 · report fixture: signature path:str/0/str · returned dict · level recorded 2026-09-25
output_json_stem src/matharena/json_zst.py ran fingerprinted MIT (permissive) · dc50b0737967bce1 · report fixture: signature path:str/0/str · returned str · level recorded 2026-09-25
parse_arxiv_version src/matharena/arxiv_source.py ran MIT (permissive) · f2a8eb492e8c00b1 · report fixture: signature value:str/0/str · returned ArxivVersion · level recorded 2026-09-25
remove_inner_boxed src/matharena/parser.py ran fingerprinted MIT (permissive) · 74e072aba194c7ff · report fixture: signature match:str/0/str · returned str · level recorded 2026-09-25
resolve_model_config_path src/matharena/arxivbench_utils.py ran MIT (permissive) · 478cd2117377963f · report fixture: signature model_arg:str/0/str, config_root:str/0/str · returned str · level recorded 2026-09-25
sha256_bytes in 6 papers src/matharena/arxivmath_source.py ran · our draft was wrong MIT (permissive) · f3f472b0143c5adf · report fixture: signature value:bytes/0/? · returned str · level recorded 2026-09-26
sha256_file in 21 papers src/matharena/arxivmath_source.py ran MIT (permissive) · 66fa4b8fdf3fcdfb · report fixture: signature path:PosixPath/0/? · returned str · level recorded 2026-09-25
sha256_text in 5 papers src/matharena/arxivmath_source.py ran · our draft was wrong fingerprinted MIT (permissive) · ba2d92a5368b72bc · report fixture: signature value:str/0/str · returned str · level recorded 2026-09-26
create_query_client src/matharena/query_client.py unverified MIT (permissive) · 9cb53e3638337514 · report
download_arxiv_artifacts src/matharena/arxiv_source.py unverified MIT (permissive) · 43400d10bfb3e09d · report
extract_source src/matharena/arxiv_source.py unverified MIT (permissive) · b00cd74d90f045f6 · report
latex2sympy_fixed src/matharena/parser.py unverified MIT (permissive) · 81a738b6f6cd0dae · report

Tasks

MathMathematical ReasoningMemorization

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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