OpenAI o3

OpenAI o3 is a reasoning model for complex analytical, coding, mathematical, and scientific tasks.

Reasoning

Added Apr 16, 2025

Pricing

Auto routing · per 1M tokens

Input: $2.00
Output: $8.00
Cache read: $1.00

Compare provider prices

Specifications

Context window: 200K
Max output: 100K
Avg output (7d): 532 tokens; Longer than 46% of models

Benchmarks

Artificial Analysis

LMArena

Sourced from Artificial Analysis.

Intelligence Index

20.2

Better than 65% of models compared

Agentic work

T²-Bench Telecom (legacy)

Legacy fallback · Conversational AI agents in dual-control scenarios

80.7%

Better than 71% of models compared

Document reasoning

AA-LCR v1.1

Long context reasoning with updated grading

74.7%

Better than 73% of models compared

Reasoning

HLE

Humanity's Last Exam

20.1%

Better than 68% of models compared

IFBench

Instruction-following benchmark

71.4%

Better than 87% of models compared

CritPt

Research-level physics reasoning

1.1%

Coding

Terminal-Bench Hard (legacy)

Legacy fallback · Agentic coding and terminal use

37.1%

Better than 84% of models compared

LiveCodeBench

Contamination-free coding benchmark

80.8%

Better than 92% of models compared

Math

AIME 2025

American Invitational Mathematics Examination 2025

88.3%

Better than 87% of models compared

AIME

American Invitational Mathematics Examination

90.3%

Better than 96% of models compared

Math-500

Diverse mathematical problem solving benchmark

99.2%

Better than 99% of models compared

Knowledge

MMLU-Pro

Professional and academic subject knowledge

85.3%

Better than 92% of models compared

AA-Omniscience Accuracy

Proportion of correctly answered questions

38.6%

AA-Omniscience Hallucination Rate

Rate of incorrect answers among non-correct responses

88.1%

Legacy benchmarks

GPQA Diamond (legacy)

Graduate-level scientific reasoning

82.7%

Better than 72% of models compared

AA-LCR (unversioned / legacy)

Long context reasoning evaluation