OpenAI: GPT-5
Analysis Summary
OpenAI's GPT-5 is a flagship model with an intelligence index of 44.6, GPQA of 0.854, HLE of 0.265, and an agentic index of 58.7. It supports vision, tool use, function calling, and file input across a 400K context window. Instruction following (ifbench 0.731) and long-context reasoning (lcr 0.756) are among the strongest in this batch, and the tau2 score of 0.848 reflects high agentic reliability.
For businesses, GPT-5 is well suited to autonomous agents, long-document analysis, complex content generation, and multimodal workflows. The 400K context window is a meaningful advantage for teams working with large codebases, lengthy contracts, or extended research documents. Vision and function calling add further breadth.
At $1.25 input and $10 output, it is expensive for high-volume use but competitive for a model at this capability level. Teams needing frontier reasoning with broad capability coverage will find GPT-5 a strong fit; those with budget constraints should consider GPT-5 Mini.
Assessed June 6, 2026
Editorial notes
GPT-5 from OpenAI delivers excellent reasoning, vision, tool use, and a 400K context window with strong instruction following and agentic performance, making it a top-tier choice for demanding business workflows.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How OpenAI: GPT-5 compares
OpenAI: GPT-5 ranks #35 of 378 AI models we track for overall intelligence, #62 of 315 for coding, #60 of 289 for agentic tasks. Its 400K-token context window is larger than 85% of the models we list. At $1.25 per million input tokens it is cheaper than 21% of comparable models.
About OpenAI: GPT-5
GPT-5 is OpenAIās 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..
Capabilities
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does OpenAI: GPT-5 stack up?
Compare side-by-side with other professional models.
Model Information
| OpenRouter ID |
openai/gpt-5
|
| Provider | openai |
| Release Date | August 7, 2025 |
| Context Length | 400,000 tokens |
| Max Completion | 128,000 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $1.25 | $0.001250 |
| Output | $10.00 | $0.010000 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
Leaderboard Categories
External Resources
Frequently asked questions about OpenAI: GPT-5
How much does OpenAI: GPT-5 cost?
OpenAI: GPT-5 costs $1.25 per million input tokens and $10.00 per million output tokens.
What is the context window of OpenAI: GPT-5?
OpenAI: GPT-5 has a context window of 400,000 tokens (400K).
Is OpenAI: GPT-5 good for coding?
On our coding benchmark index, OpenAI: GPT-5 ranks #62 of 315 models, placing it in the top quartile of the field for code generation and debugging.
What can OpenAI: GPT-5 do?
OpenAI: GPT-5 supports image/vision input, tool use, and function calling.
Who created OpenAI: GPT-5?
OpenAI: GPT-5 is developed by OpenAI and was released on August 7, 2025.
