ChatGPT
Chat app · Other models- 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
38.1#26 of 83measured models
Measured · Artificial Analysis v4.3.2- API price from
- $0.10 in / $0.50 out / 1M tokOpenAI · direct API
- Context window
- 1.05M tok
Performance profile
CodingRank #20 of 94
54.6%
SciCodeCost efficiencyRank #6 of 67
562.1pts / $
Intelligence ÷ eval costCapabilities
Context window
Modalities
Integration
Reasoning trade-offs
Source (opens in a new tab)GPT-6 Luna
Cost per task (USD) · log scale
GPT-6 LunaMax
- Intelligence Index
- 38.1
- Cost / task
- $0.0678
- Evaluation time
- 7.0m
Pricing & access
API route
OpenAIAPI
OpenAIAPITier & context
USD per 1M tokens
- Input
- $0.10
- Output
- $0.50
- Cached input
- $0.01
- Cache write
- $0.125
Responses API tool compatibility (opens in a new tab)
- Web search
- File search
- Image generation
- Code execution
- Shell
- File edits
- Skills
- Computer use
- MCP
- Tool search
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/mo
- Go
- $8/moAccess not verified
- Plus
- $20/mo
- 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)38.5%, rank 29 of 12654.6%, rank 20 of 9412.6%, rank 25 of 8783.3%, rank 10 of 1251,432 Elo, rank 28 of 101
Humanity’s Last Exam
Frontier reasoning- 1Claude Opus 5.5Max61.4%
- 2Claude Fable 5.1Max59.1%
- 3Gemini 4 ArgonHigh57.1%
- 26Ling-3.1-flashReasoning39.4%
- 27DeepSeek-V4.1-FlashMax39.2%
- 28MiniMax-M3Reasoning39.0%
- 29GPT-6 LunaMax38.5%
- 30Agnes 3.0 FlashReasoning38.5%
- 31Qwen3.8-Flash-NextReasoning38.0%
- 32Agnes 2.5 Pro BetaReasoning37.5%
Peers use their best measured result on this benchmark.
Alternatives
- Scores higherMistral Large 4Reasoning
- Intelligence Index
- 38.4+0.3
- Cost / task
- $1.13+1572%
- More from OpenAI
- Intelligence Index
- 42.1+4.0
- Cost / task
- $1.40+1962%
- Similar scoreMiMo-V2.6-FlashReasoning
- Intelligence Index
- 37.9−0.2
- Cost / task
- $0.062−8%
Each model at its highest-scoring measured setting · Intelligence Index v4.3.2 and its evaluation cost per task.