SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.07985 · 2024

Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models

arXiv · PDF · Open in the Atlas

Code that ran

13 of 19 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; 1 honoured the contract we drafted, 5 violated it and 0 have no contract verdict; 7 failures of our instrument; 6 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/2410.07985.json · badge: /api/ran/2410.07985.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
kbsdjames/omni-math-rule canonical (classifier label)
classifier basis: census
11 ran · 2 no recorded run
kbsdjames/omni-math canonical (classifier label)
classifier basis: census
2 ran · 4 no recorded run
FunctionStatusWhere it lives
choice_answer_clean Ran
ran; our contract draft was wrong, not the code
kbsdjames/omni-math-rule/evaluation/grader.py
pointer only (licence: NONE); the stored copy get_code serves, from QwenLM/Qwen2.5-Math, is pointer only (licence: NONE) · get_code("809c0178a7ae90ff")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kbsdjames/omni-math-rule when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

compare_numerical_ans Ran
ran, violated the contract we drafted
kbsdjames/omni-math-rule/evaluation/math_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from QwenLM/Qwen2.5-Math, is pointer only (licence: NONE) · get_code("81082f28e1440f9d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kbsdjames/omni-math-rule when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

extract_multi_choice_answer Ran
ran; our contract draft was wrong, not the code
kbsdjames/omni-math-rule/evaluation/parser.py
pointer only (licence: NONE); the stored copy get_code serves, from QwenLM/Qwen2.5-Math, is pointer only (licence: NONE) · get_code("ed2f4689128f9885")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kbsdjames/omni-math-rule when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

generate_completions Ran
ran; our contract draft was wrong, not the code
kbsdjames/omni-math-rule/evaluation/model_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from fanqiwan/FuseAI, is pointer only (licence: NONE) · get_code("1525d8bc0fc8d5a0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kbsdjames/omni-math-rule when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

is_digit Ran
ran, violated the contract we drafted
kbsdjames/omni-math-rule/evaluation/grader.py
pointer only (licence: NONE); the stored copy get_code serves, from QwenLM/Qwen2.5-Math, is pointer only (licence: NONE) · get_code("fb37d3c84b18e368")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kbsdjames/omni-math-rule when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

is_execution_success Ran
ran, violated the contract we drafted
kbsdjames/omni-math-rule/evaluation/trajectory.py
pointer only (licence: NONE); the stored copy get_code serves, from QwenLM/Qwen2.5-Math, is pointer only (licence: NONE) · get_code("581f3949cfdcffa2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kbsdjames/omni-math-rule when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

is_multi_choice Ran
ran, violated the contract we drafted
kbsdjames/omni-math-rule/evaluation/math_eval.py
pointer only (licence: NONE) · get_code("d338a8cb44aeb6b4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kbsdjames/omni-math-rule when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

is_number Ran
ran, violated the contract we drafted
kbsdjames/omni-math-rule/evaluation/math_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from QwenLM/Qwen2.5-Math, is pointer only (licence: NONE) · get_code("1c1060f6e43d5dfa")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kbsdjames/omni-math-rule when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

parse_digits Ran
ran, honoured the contract we drafted
kbsdjames/omni-math-rule/evaluation/grader.py
pointer only (licence: NONE); the stored copy get_code serves, from QwenLM/Qwen2.5-Math, is pointer only (licence: NONE) · get_code("7d4b7f8c3875b126")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kbsdjames/omni-math-rule when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

parse_report Ran
ran; our contract draft was wrong, not the code
kbsdjames/omni-math/Omni-Judge_eval/get_result.py
pointer only (licence: NONE) · get_code("b50ea41b74e077ce")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kbsdjames/omni-math when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

text_to_trajectory Ran
ran; our contract draft was wrong, not the code
kbsdjames/omni-math-rule/evaluation/trajectory.py
pointer only (licence: NONE); the stored copy get_code serves, from QwenLM/Qwen2.5-Math, is pointer only (licence: NONE) · get_code("7e48538d19cc0d8f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kbsdjames/omni-math-rule when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

trajectory_to_text Ran
ran; our contract draft was wrong, not the code
kbsdjames/omni-math-rule/evaluation/trajectory.py
pointer only (licence: NONE); the stored copy get_code serves, from QwenLM/Qwen2.5-Math, is pointer only (licence: NONE) · get_code("0d7ae684ec6c7537")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kbsdjames/omni-math-rule when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

update_domain Ran
ran; our contract draft was wrong, not the code
kbsdjames/omni-math/GPT_eval/detailed_evaluation/domain_specific_evaluation.py
pointer only (licence: NONE) · get_code("bd9fc2c45d3b49d6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kbsdjames/omni-math when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_batch_responses Not yet run
unverified (harvested, no recorded run)
kbsdjames/omni-math/Omni-Judge_eval/omni_judge.py
pointer only (licence: NONE) · get_code("3b59d56c92000709")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kbsdjames/omni-math when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

load_hf_lm_and_tokenizer Not yet run
unverified (harvested, no recorded run)
kbsdjames/omni-math-rule/evaluation/model_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from YangLing0818/SuperCorrect-llm, is pointer only (licence: NONE) · get_code("ee71a94d9dd1b8e9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kbsdjames/omni-math-rule when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

main Not yet run
unverified (harvested, no recorded run)
kbsdjames/omni-math/Omni-Judge_eval/detailed_evaluation/difficulty_specific_evaluation.py
pointer only (licence: NONE) · get_code("a2095803e48965a1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kbsdjames/omni-math when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

main Not yet run
unverified (harvested, no recorded run)
kbsdjames/omni-math/GPT_eval/detailed_evaluation/difficulty_specific_evaluation.py
pointer only (licence: NONE) · get_code("b7f72b95c867a1ec")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kbsdjames/omni-math when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

my_parse_latex Not yet run
unverified (harvested, no recorded run)
kbsdjames/omni-math-rule/evaluation/math_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from QwenLM/Qwen2.5-Math, is pointer only (licence: NONE) · get_code("73925940858a62b3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kbsdjames/omni-math-rule when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

update_domain Not yet run
unverified (harvested, no recorded run)
kbsdjames/omni-math/Omni-Judge_eval/detailed_evaluation/domain_specific_evaluation.py
pointer only (licence: NONE) · get_code("7df9161529866271")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kbsdjames/omni-math when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 19 samples lifted from this paper's linked repositories, 19 carry a function identity and 0 do not. Of the 19 distinct functions with an identity, 13 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 1 the same month, 13 later) and 6 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.

FunctionAlso present inEarliest-datedOthers named
is_digit 18 other papers
1 dated earlier, 16 later, 1 undated
2405.14365 (2024-05)
JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models
2502.06703 (2025-02)
Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling
2502.06773 (2025-02)
On the Emergence of Thinking in LLMs I: Searching for the Right Intuition
and 15 more not named here
load_hf_lm_and_tokenizer 18 other papers
2 dated earlier, 1 the same month, 15 later
2405.14365 (2024-05)
JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models
2408.07471 (2024-08)
Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization
2410.09008 (2024-10)
SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction
and 15 more not named here
parse_digits 18 other papers
1 dated earlier, 16 later, 1 undated
2405.14365 (2024-05)
JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models
2502.06703 (2025-02)
Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling
2502.06773 (2025-02)
On the Emergence of Thinking in LLMs I: Searching for the Right Intuition
and 15 more not named here
generate_completions 17 other papers
2 dated earlier, 15 later
2405.14365 (2024-05)
JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models
2408.07471 (2024-08)
Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization
2412.03187 (2024-12)
Weighted-Reward Preference Optimization for Implicit Model Fusion
and 14 more not named here
choice_answer_clean 15 other papers
14 later, 1 undated
2502.06703 (2025-02)
Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling
2502.06773 (2025-02)
On the Emergence of Thinking in LLMs I: Searching for the Right Intuition
2502.12215 (2025-02)
Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?
and 12 more not named here
extract_multi_choice_answer 12 other papers
2 dated earlier, 9 later, 1 undated
2405.14365 (2024-05)
JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models
2408.03314 (2024-08)
Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
2502.06773 (2025-02)
On the Emergence of Thinking in LLMs I: Searching for the Right Intuition
and 9 more not named here
is_multi_choice 8 other papers
1 dated earlier, 7 later
2309.00071 (2023-09)
YaRN: Efficient Context Window Extension of Large Language Models
2502.06773 (2025-02)
On the Emergence of Thinking in LLMs I: Searching for the Right Intuition
2503.18892 (2025-03)
SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild
and 5 more not named here
compare_numerical_ans 6 other papers
1 dated earlier, 5 later
2405.14365 (2024-05)
JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models
2504.05185 (2025-04)
Concise Reasoning via Reinforcement Learning
2504.20571 (2025-04)
Reinforcement Learning for Reasoning in Large Language Models with One Training Example
and 3 more not named here
is_number 6 other papers
1 dated earlier, 5 later
2405.14365 (2024-05)
JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models
2504.05185 (2025-04)
Concise Reasoning via Reinforcement Learning
2504.20571 (2025-04)
Reinforcement Learning for Reasoning in Large Language Models with One Training Example
and 3 more not named here
my_parse_latex 6 other papers
1 dated earlier, 5 later
2405.14365 (2024-05)
JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models
2504.05185 (2025-04)
Concise Reasoning via Reinforcement Learning
2504.20571 (2025-04)
Reinforcement Learning for Reasoning in Large Language Models with One Training Example
and 3 more not named here
is_execution_success 3 other papers
3 later
2502.06773 (2025-02)
On the Emergence of Thinking in LLMs I: Searching for the Right Intuition
2504.05185 (2025-04)
Concise Reasoning via Reinforcement Learning
2604.11056 (2026-04)
Where Hindsight Credit Can Reside: A Signed-Capacity View of Token Updates in RLVR
text_to_trajectory 3 other papers
3 later
2502.06773 (2025-02)
On the Emergence of Thinking in LLMs I: Searching for the Right Intuition
2504.05185 (2025-04)
Concise Reasoning via Reinforcement Learning
2604.11056 (2026-04)
Where Hindsight Credit Can Reside: A Signed-Capacity View of Token Updates in RLVR
trajectory_to_text 3 other papers
3 later
2502.06773 (2025-02)
On the Emergence of Thinking in LLMs I: Searching for the Right Intuition
2504.05185 (2025-04)
Concise Reasoning via Reinforcement Learning
2604.11056 (2026-04)
Where Hindsight Credit Can Reside: A Signed-Capacity View of Token Updates in RLVR

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

Recent advancements in large language models (LLMs) have led to significant breakthroughs in mathematical reasoning capabilities. However, existing benchmarks like GSM8K or MATH are now being solved with high accuracy (e.g., OpenAI o1 achieves 94.8\% on MATH dataset), indicating their inadequacy for truly challenging these models. To bridge this gap, we propose a comprehensive and challenging benchmark specifically designed to assess LLMs' mathematical reasoning at the Olympiad level. Unlike existing Olympiad-related benchmarks, our dataset focuses exclusively on mathematics and comprises a vast collection of 4428 competition-level problems with rigorous human annotation. These problems are meticulously categorized into over 33 sub-domains and span more than 10 distinct difficulty levels, enabling a holistic assessment of model performance in Olympiad-mathematical reasoning. Furthermore, we conducted an in-depth analysis based on this benchmark. Our experimental results show that even the most advanced models, OpenAI o1-mini and OpenAI o1-preview, struggle with highly challenging Olympiad-level problems, with 60.54\% and 52.55\% accuracy, highlighting significant challenges in Olympiad-level mathematical reasoning.

For agents

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

get_harvested_code_for_paper("2410.07985")
get_code_for_paper("2410.07985")
have("2410.07985")

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

curl https://syntology.ai/api/ran/2410.07985.json

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

[![Syntology run record](https://syntology.ai/api/ran/2410.07985.svg)](https://syntology.ai/paper/2410.07985)

Connect an agent — have() is free.