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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2505.23281")

Code

Syntology Ran 0 of 19 code samples harvested from 1 repository linked to this paper; 19 have no recorded run.

By repository: official repository: 19 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

eth-sri/matharena officialmentioned in paperMIT 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; 0 ran; 0 honoured the contract we drafted; 19 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

19unverified

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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

check_number_proximity_any_order eth-sri/matharena/src/matharena/grader.py official repository unverified MIT (permissive) · cebd63ce42db8cf0 · report
create_query_client eth-sri/matharena/src/matharena/query_client.py official repository unverified MIT (permissive) · 9cb53e3638337514 · report
download_arxiv_artifacts eth-sri/matharena/src/matharena/arxiv_source.py official repository unverified MIT (permissive) · 43400d10bfb3e09d · report
exclude_configs eth-sri/matharena/src/matharena/configs.py official repository unverified MIT (permissive) · 3c24b8cb7ab88e6d · report
extract_numbers eth-sri/matharena/src/matharena/grader.py official repository unverified MIT (permissive) · 811a3d879ce72f27 · report
extract_source eth-sri/matharena/src/matharena/arxiv_source.py official repository unverified MIT (permissive) · b00cd74d90f045f6 · report
find_last_boxed_content eth-sri/matharena/src/matharena/parser.py official repository unverified MIT (permissive) · d8d2c5ba39e34d5f · report
latex2sympy_fixed eth-sri/matharena/src/matharena/parser.py official repository unverified MIT (permissive) · 81a738b6f6cd0dae · report
load_configs eth-sri/matharena/src/matharena/configs.py official repository unverified MIT (permissive) · 19d49ff9409d85f2 · report
load_json_zst eth-sri/matharena/src/matharena/json_zst.py official repository unverified MIT (permissive) · b8de5523615a315e · report
load_metadata eth-sri/matharena/src/matharena/arxivbench_utils.py official repository unverified MIT (permissive) · d2318c1b39c8b47e · report
load_model_config eth-sri/matharena/src/matharena/arxivbench_utils.py official repository unverified MIT (permissive) · 1556226ccd07a184 · report
output_json_stem eth-sri/matharena/src/matharena/json_zst.py official repository unverified MIT (permissive) · dc50b0737967bce1 · report
parse_arxiv_version eth-sri/matharena/src/matharena/arxiv_source.py official repository unverified MIT (permissive) · f2a8eb492e8c00b1 · report
remove_inner_boxed eth-sri/matharena/src/matharena/parser.py official repository unverified MIT (permissive) · 74e072aba194c7ff · report
resolve_model_config_path eth-sri/matharena/src/matharena/arxivbench_utils.py official repository unverified MIT (permissive) · 478cd2117377963f · report
sha256_bytes eth-sri/matharena/src/matharena/arxivmath_source.py official repository unverified MIT (permissive) · f3f472b0143c5adf · report
sha256_file eth-sri/matharena/src/matharena/arxivmath_source.py official repository unverified MIT (permissive) · 66fa4b8fdf3fcdfb · report
sha256_text eth-sri/matharena/src/matharena/arxivmath_source.py official repository unverified MIT (permissive) · ba2d92a5368b72bc · 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