MATH (CoT)Math
98.2/ 100
Verified
Last Verified: Unknown DateOpenAI Blog
Challenging competition mathematics problems (AIME/IMO level).
Beta version: *Information might not be fully accurate. Please report any discrepancies.
Beta version: *Information might not be fully accurate. Please report any discrepancies.
Latest Data
2026-02-20
Context Window
200k
tokens
Input Cost
$2.00
per 1M tokens
Output Cost
$8.00
per 1M tokens
Cache Cost
$0.50 / Free
read / write per 1M
Parameters
Reasoning Model
model footprint
Performance Analysis // Verified Benchmarks
Challenging competition mathematics problems (AIME/IMO level).
Contamination-free, continuously updated reasoning benchmark.
Next-generation HumanEval with more diverse library calls and complex tasks.
American Invitational Mathematics Examination. Competition-level math.
Artificial Analysis aggregate intelligence index.
Comprehensive framework to evaluate LLMs as agents across diverse environments.
A more robust and harder version of MMLU, focusing on complex reasoning and STEM subjects.
Humanity's Last Exam - Hard reasoning benchmark without tools.
Artificial Analysis aggregate math capability index.
500-problem math benchmark for broad quantitative reasoning.
Contamination-free coding benchmark using recent problems.
Artificial Analysis aggregate coding capability index.
Graduate-Level Google-Proof Q&A Benchmark.
Artificial Analysis Long Context Reasoning benchmark. Evaluates reasoning over long contexts.
Artificial Analysis IFBench. Evaluates precise instruction following with constraints.
American Invitational Mathematics Examination 2025 problems.
Expert-level chemistry knowledge and reasoning.
Hard split of Terminal-Bench focused on tougher terminal workflows.
Telecom-domain tool-use and workflow benchmark.
Scientific programming benchmark for code synthesis and correctness.