GPT 5
GPT-5 is OpenAI's most advanced model, offering major improvements in reasoning, code quality, and user experience. It handles complex coding tasks with minimal prompting, provides clear explanations, and introduces enhanced agentic capabilities. Designed for logic and multi-step tasks.
- Reasoning
- Vision
- Native PDF input
- Tool Calling
- Structured Output
Added Aug 7, 2025
Pricing
Auto routing · per 1M tokens- Input
- $1.25
- Output
- $10.00
- Cache read
- $0.13
Specifications
- Context window
- 400K
- Max output
- 128K
- Avg output (7d)
- 665 tokens
- Longer than 57% of models
Benchmarks
Benchmarks
Sourced from Artificial Analysis.
Intelligence Index
23.0
Coding Index
37.8
Agentic work
T²-Bench Telecom (legacy)
Legacy fallback · Conversational AI agents in dual-control scenarios
84.8%
Better than 76% of models compared
GDPval-AA v2
Economically valuable tasks (Elo)
920 Elo
Better than 40% of models compared
Document reasoning
AA-LCR v1.1
Long context reasoning with updated grading
78.2%
Better than 80% of models compared
Reasoning
HLE
Humanity's Last Exam
28.5%
Better than 76% of models compared
IFBench
Instruction-following benchmark
73.1%
Better than 90% of models compared
CritPt
Research-level physics reasoning
5.7%
Coding
Terminal-Bench Hard (legacy)
Legacy fallback · Agentic coding and terminal use
32.6%
Better than 76% of models compared
LiveCodeBench
Contamination-free coding benchmark
84.6%
Better than 95% of models compared
Math
AIME 2025
American Invitational Mathematics Examination 2025
94.3%
Better than 95% of models compared
AIME
American Invitational Mathematics Examination
95.7%
Better than 99% of models compared
Math-500
Diverse mathematical problem solving benchmark
99.4%
Better than 99% of models compared
Knowledge
MMLU-Pro
Professional and academic subject knowledge
87.1%
Better than 97% of models compared
AA-Omniscience Accuracy
Proportion of correctly answered questions
40.3%
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
82.2%
Legacy benchmarks
GPQA Diamond (legacy)
Graduate-level scientific reasoning
85.4%
Better than 78% of models compared
AA-LCR (unversioned / legacy)
Long context reasoning evaluation
78.2%
Better than 79% of models compared
GDPval-AA (unversioned / legacy)
Economically valuable tasks
20.8%
Last updated Oct 15, 2026
Artificial AnalysisProviders
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…