About GPT-5
GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like "think hard about this." Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.
Specifications
- Provider
- OpenAI
- Context Length
- 400,000 tokens
- Input Types
- text, image, file
- Output Types
- text
- Category
- GPT
- Added
- 8/7/2025
Benchmark Performance
How GPT-5 compares to its closest rivals across industry benchmarks
Evaluates AI ability to resolve real GitHub issues from Python repositories
Metric: % Resolved
30 problems from the 2025 American Invitational Mathematics Examination testing olympiad-level math reasoning
Metric: Accuracy %
#5
Claude-Opus-4.1 (Think)
25.6
Challenging math contest benchmark featuring the most difficult olympiad-level problems
Metric: Accuracy %
#5
Claude-Opus-4.1 (Think)
25.6
Comprehensive comparison of AI models across intelligence, price, speed, and latency
Metric: Intelligence Index
#9
MiMo-V2-Flash
66.0
#16
MiniMax-M2.1
64.0
#17
KAT-Coder-Pro V1
64.0
Comparison with GPT-4o (extended)
| Specification | GPT-4o (extended) Previous | GPT-5 Current | Change |
|---|---|---|---|
| Context Window | 128K | 400K | |
| Reasoning Support | |||
| Input Types | text, image, file | text, image, file | |
| Output Types | text | text | |
| LMArena Score | 1440 | 1455 | |
| Input Price (per 1M) | $6.00 | $1.25 | |
| Output Price (per 1M) | $18.00 | $10.00 |
Frequently Asked Questions
Common questions about GPT-5