Back to models
Intelligence Index
Extra high setting
46.4#10 of 83measured models
Measured · Artificial Analysis v4.3.2- API price from
- $2.00 in / $6.00 out / 1M tokOpenRouter · xAI
- Context window
- 500K tok
Performance profile
CodingRank #14 of 94
57.4%
SciCodeCost efficiencyRank #62 of 67
12.4pts / $
Intelligence ÷ eval costCapabilities
Context window
Modalities
Integration
Reasoning trade-offs
Source (opens in a new tab)Grok 4.7
Cost per task (USD)
Grok 4.7Xhigh
- Intelligence Index
- 46.4
- Cost / task
- $3.74
- Evaluation time
- 13.7m
Pricing & access
USD per 1M tokens
- Input
- $2.00
- Output
- $6.00
- Cached input
- $0.50
Benchmarks
Full leaderboardSource (opens in a new tab)43.1%, rank 18 of 12657.4%, rank 14 of 9425.8%, rank 20 of 8776.7%, rank 46 of 1251,711 Elo, rank 6 of 101
Humanity’s Last Exam
Frontier reasoning- 1Claude Opus 5.5Max61.4%
- 2Claude Fable 5.1Max59.1%
- 3Gemini 4 ArgonHigh57.1%
- 15Claude Haiku 5.5Max44.4%
- 16Muse Spark OpenExtra high43.9%
- 17JT-4.1 Flash 236B A21BReasoning43.6%
- 18Grok 4.7Extra high43.1%
- 19Qwen3.8 Max (0902)Reasoning43.1%
- 20GPT-5.6 TerraMax42.9%
- 21GPT-5.3-CodexExtra high42.5%
Peers use their best measured result on this benchmark.
Alternatives
- Scores higher
- Intelligence Index
- 48.1+1.6
- Cost / task
- $1.60−57%
- Higher score, lower costPublic API and app accessGemini 4 ArgonHigh
- Intelligence Index
- 52.6+6.1
- Cost / task
- $1.99−47%
- Similar scoreMiMo-V2.6-ProReasoning
- Intelligence Index
- 46.3−0.1
- Cost / task
- $0.133−96%
Each model at its highest-scoring measured setting · Intelligence Index v4.3.2 and its evaluation cost per task.