ChatGPT
Chat app- Web search
- Files
- Code execution
- Image generation
Back to modelsOpen ChatGPT Work (opens in a new tab) Open Codex (opens in a new tab)
Intelligence Index
Max setting
52.7#5 of 83measured models
Measured · Artificial Analysis v4.3.2- API price from
- $10.00 in / $50.00 out / 1M tokOpenAI · direct API
- Context window
- 1.05M tok
Performance profile
ReasoningRank #1 of 107
96.1%
GPQA DiamondCodingRank #16 of 94
56.5%
SciCodeCost efficiencyRank #60 of 67
16.2pts / $
Intelligence ÷ eval costCapabilities
Context window
Modalities
Integration
Reasoning trade-offs
Source (opens in a new tab)GPT-6 Astra
Cost per task (USD) · log scale
GPT-6 AstraMax
- Intelligence Index
- 52.7
- Cost / task
- $3.26
- Evaluation time
- 7.9m
Pricing & access
API route
OpenAIAPI
OpenAIAPITier & context
USD per 1M tokens
- Input
- $10.00
- Output
- $50.00
- Cached input
- $1.00
- Cache write
- $12.50
Responses API tool compatibility (opens in a new tab)
- Web search
- File search
- Code execution
- Computer use
- MCP
Open ChatGPT (opens in a new tab)
ChatGPT Work
Work agent- Files
- Browser
- Connected apps
Codex
Coding agent- Files
- Shell
Available plans · USD
All plans for ChatGPT (opens in a new tab)Personal
- Free
- $0/moNot included
- Go
- $8/moAccess not verified
- Plus
- $20/moChatGPT Work · Codex
- Pro 100
- $100/mo
- Pro 200
- $200/mo
- Pro 500
- $500/mo
Organizations4 plans
- Business Standard
- $25/seat/mo
- Business Premium
- $125/seat/mo
- Enterprise
- Custom
- Edu
- Custom
Benchmarks
Full leaderboardSource (opens in a new tab)54.7%, rank 5 of 12656.5%, rank 16 of 9459.1%, rank 3 of 8780.7%, rank 26 of 1251,573 Elo, rank 21 of 101
Humanity’s Last Exam
Frontier reasoning- 1Claude Opus 5.5Max61.4%
- 2Claude Fable 5.1Max59.1%
- 3Gemini 4 ArgonHigh57.1%
- 4Claude Sonnet 5.5Max55.0%
- 5GPT-6 AstraMax54.7%
- 6Muse Wonder FullMax53.6%
- 7GPT-6.1 SolMax52.9%
- 8Muse WonderMax50.1%
- 9MiMo-V2.6-ProReasoning49.4%
- 10Muse Spark 1.3Max48.7%
Peers use their best measured result on this benchmark.
Alternatives
- Scores higher
- Intelligence Index
- 53.4+0.7
- Cost / task
- $7.63+134%
- Lower cost, close scoreGPT-6.1 SolMax
- Intelligence Index
- 51.8−0.8
- Cost / task
- $0.724−78%
- More from OpenAI
- Intelligence Index
- 42.1−10.6
- Cost / task
- $1.40−57%
Each model at its highest-scoring measured setting · Intelligence Index v4.3.2 and its evaluation cost per task.