OpenAI: GPT-5
GPT-5 from OpenAI is designed for handling extensive text inputs up to 400,000 tokens and supports processing images and files, making it versatile for various tasks. It can reason about structured data and external tools, though it does not generate fully structured outputs. With a blended benchmark score of 69.7 across four independent evaluations, GPT-5 performs well in polyglot assistance but lags in coding-specific tasks. Given its pricing at $1.25 per million input tokens and $10.0 per million output tokens, it is more suited for users requiring extensive context processing and reasoning capabilities who can afford the higher cost.
Benchmark results
Independent, published benchmarks. Blended score 69.7 across 4 benchmarks, last refreshed 2026-08-13. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| Aider Polyglot | code editing across languages | 88.0 |
| AI Index | broad capability composite | 58.3 |
| AI Index Coding | software engineering tasks | 62.3 |
| AI Index Agentic | multi-step tool-using tasks | 43.8 |
- Model ID
- openai/gpt-5
- Vendor
- openai
- Released
- August 2025
- Tokenizer
- GPT
- Input Modalities
- text, image, file
- Output Modalities
- text
- Max Output
- 128,000 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- ✓ accepts images
- Audio
- no
- Moderated
- yes
What it costs in practice
Computed from the current $1.25/M input and $10.00/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | $0.05 |
| Classify 1,000 customer emails | 500k in / 50k out | $1.12 |
| A month of a busy support chatbot | 5M in / 2M out | $26.25 |
Category rankings
Where OpenAI: GPT-5 places across the 39 categories it ranks in. How we rank →
| # | Category | Score |
|---|---|---|
| #12 | SOP / Process DocsBusiness · of 25 ranked | 138 |
| #15 | CSV / Spreadsheet CleanupData · of 25 ranked | 155 |
| #17 | Fitness CoachingPersonal · of 25 ranked | 136 |
| #18 | Experiment DesignResearch · of 25 ranked | 159 |
| #19 | Unit Test GenerationCode · of 25 ranked | 156 |
| #20 | Diagram ExtractionVision · of 25 ranked | 150 |
| #21 | CI/CD PipelinesCode · of 25 ranked | 146 |
| #21 | Frontend Component DesignCode · of 25 ranked | 147 |
| #21 | ETL ScriptingData · of 25 ranked | 156 |
| #21 | Medical Note SummarizationProfessional · of 25 ranked | 156 |
| #21 | Chart & Graph ReadingVision · of 25 ranked | 152 |
| #22 | Code ReviewCode · of 25 ranked | 169 |
| #22 | Code RefactoringCode · of 25 ranked | 166 |
| #22 | OCR / Document ParsingData · of 25 ranked | 147 |
| #22 | Table Extraction from PDFsData · of 25 ranked | 147 |
| #22 | Legal ResearchProfessional · of 25 ranked | 169 |
| #22 | Contract ReviewProfessional · of 25 ranked | 179 |
| #22 | Scientific ResearchProfessional · of 25 ranked | 169 |
| #22 | Math TutoringEducation · of 25 ranked | 149 |
| #22 | History TutoringEducation · of 25 ranked | 146 |
| #22 | Essay GradingEducation · of 25 ranked | 169 |
| #22 | RFP ResponseBusiness · of 25 ranked | 176 |
| #22 | RAG PipelinesAgents · of 25 ranked | 166 |
| #22 | Long-Context Q&AAgents · of 25 ranked | 156 |
| #22 | Fiction CollaboratorPersonal · of 25 ranked | 169 |
| #22 | Literature ReviewResearch · of 25 ranked | 169 |
| #24 | Physics TutoringEducation · of 25 ranked | 149 |
| #24 | Screenshot DebuggingVision · of 25 ranked | 142 |
| #25 | Regex WritingCode · of 25 ranked | 135 |
| #25 | Creative WritingWriting · of 25 ranked | 159 |
| #25 | Screenwriting & DialogWriting · of 25 ranked | 159 |
| #25 | Language TranslationWriting · of 25 ranked | 135 |
| #25 | Academic WritingWriting · of 25 ranked | 159 |
| #25 | Legal DraftingProfessional · of 25 ranked | 159 |
| #25 | Meeting NotesBusiness · of 25 ranked | 150 |
| #25 | Resume WritingBusiness · of 25 ranked | 117 |
| #25 | OKRs & Strategic PlanningBusiness · of 25 ranked | 159 |
| #25 | Tutoring for KidsPersonal · of 25 ranked | 135 |
| #25 | Math ProofsResearch · of 25 ranked | 159 |
Similar models
OpenAI: GPT-5.6 Luna Pro
OpenAI: GPT-5.6 Luna Pro (batch)
OpenAI: GPT-5.6 Luna
OpenAI: GPT-5.6 Luna (batch)
OpenAI: GPT-5.6 Terra Pro
OpenAI: GPT-5.6 Terra Pro (batch)
Quick answers
- How much does OpenAI: GPT-5 cost?
- $1.25 per million input tokens and $10.00 per million output tokens.
- What is OpenAI: GPT-5's context window?
- 400,000 tokens, roughly 600 pages of text in a single request.
- Does OpenAI: GPT-5 support tool calling?
- It supports tool calling, structured output, a reasoning mode.
- Can OpenAI: GPT-5 process images?
- Yes, it accepts image input.