o3-deep-research is OpenAI's most advanced model for deep research, designed to tackle complex, multi-step research tasks. It can search and synthesize information from across the internet as well as from your own data.
Added Jan 31, 2026
Context Window
200.0K
Max Output
100.0K
Input Price (Auto)
$11.00/1M
Output Price (Auto)
$44.00/1M
Cache Read (Auto)
$5.50/1M
Capabilities
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
38.4
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Coding Index
38.4
GPQA Diamond
Graduate-level scientific reasoning
82.7%
Better than 86% of models compared
HLE
Humanity's Last Exam
20.0%
Better than 88% of models compared
IFBench
Instruction-following benchmark
71.4%
Better than 91% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
80.7%
Better than 77% of models compared
AA-LCR
Long context reasoning evaluation
69.3%
Better than 95% of models compared
SciCode
Python programming for scientific computing
41.0%
Better than 87% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
37.1%
Better than 90% of models compared
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
MMLU-Pro
Professional and academic subject knowledge
85.3%
Better than 92% of models compared
Last updated May 15, 2026
Artificial AnalysisLiveCodeBench
Contamination-free coding benchmark
80.8%
Better than 92% of models compared
Math-500
Diverse mathematical problem solving benchmark
99.2%
Better than 99% of models compared
