NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/Grok 4.7
xAI logo

Grok 4.7

by xAI · Released Sep 2026

Multimodal
55.6
avg score
Rank #120
Compare
Better than 63% of all models
Context
500K tokens (~250 books)
Input $/1M
$2.00
Output $/1M
$6.00
Type
multimodal
License
Proprietary
Benchmarks
23 tested
Data as of
About

Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and...

Tested on 23 benchmarks · BenchGecko score 55.6. Top scores: OTIS Mock AIME 2024-2025 (98.0%), GPQA diamond (94.1%), Dtbench (93.3%).

Looking for similar performance at lower cost?
GPT-5 Mini scores 55.8 (100% as good) at $0.25/1M input · 88% cheaper
Capabilities
coding
38.5
#146 globally
reasoning
75.8
#36 globally
math
57.0
#111 globally
knowledge
52.2
#119 globally
agentic
54.6
#21 globally
general
39.8
#82 globally
speed
50.3
#34 globally
Benchmark Scores
Compare All
Tested on 23 benchmarks · Ranked across 7 categories
Score Distribution (all 326 models)
0255075100
▲ You are here
codingCompare coding →
Frontiercode
47.6·
Frontierswe
29.5·
reasoningCompare reasoning →
ARC-AGI

Abstraction and Reasoning Corpus. Tests fluid intelligence through novel visual pattern recognition puzzles. Core measure of general intelligence.

90.2·
ARC-AGI-2

ARC-AGI 2, harder sequel to ARC. More complex abstract reasoning patterns that test generalization ability beyond training data.

61.4·
mathCompare math →
OTIS Mock AIME 2024-2025

Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.

98.0·
FrontierMath-Tiers-1-3-v2-Private
55.8·
FrontierMath-Tier-4-v2-Private
17.1·
Quick compare:vs Dolphin 2.9.1 Yi 1.5 34bOpenAI logovs GPT-5 MiniDeepSeek logovs R1 0528
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Model Family · xAI Grok 4.7
Sep 2026
55.6
$2.00/M in500Kctx23 benchmarks
Sep 2026
$1.60/M in(-0.40)500Kctx
See the full Grok 4.7 family →
Recently Happened
Grok 4.7 pricing increased 25%
Sep 29, 2026
Grok 4.7 added
Sep 22, 2026
Similar Models
Dolphin 2.9.1 Yi 1.5 34b
DPHN
55.6n/a
OpenAI logo
GPT-5 Mini
OpenAI
55.8$0.25/1M
DeepSeek logo
R1 0528
DeepSeek
55.4$0.50/1M
Links
Info
xAIPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@xAI
BenchGecko API
grok-4-7
Specifications
  • Typemultimodal
  • Context500K tokens (~250 books)
  • ReleasedSep 2026
  • LicenseProprietary
  • StatusActive
  • Cost / Message~$0.010
Available On
xAI logoxAI$2.00
Categories
codingreasoningmathknowledgeagenticgeneralspeed
Learn More
context-windowtransformertokens
Share & Export
Tweet
Related Models
Dolphin 2.9.1 Yi 1.5 34b
55.6
OpenAI logoGPT-5 Mini
55.8
DeepSeek logoR1 0528
55.4
OpenAI logoGPT-5.2
55.3
Grok 4.7 is a proprietary multimodal AI model by xAI, released in September 2026. It has an average benchmark score of 55.6. Context window: 500K tokens.

Related Models

Dolphin 2.9.1 Yi 1.5 34b · DPHNGPT-5 Mini · OpenAIR1 0528 · DeepSeekGPT-5.2 · OpenAIGrok 4.20 · xAI

Benchmarks

OTIS Mock AIME 2024-2025GPQA diamondDtbenchARC-AGIArtificial Analysis · Long Context Reasoning

Related Pages

xAI · ProviderxAI · EconomyAll ModelsCompare ModelsPricingDevelopers · APIContext Window · Glossary

Key facts · as of 2026-11-11

  • Grok 4.7 by xAI. BenchGecko score 55.6, rank 120 of 326 scored models (normalized average of public benchmark scores).
  • List price $2.00 input · $6.00 output per 1M tokens (as of 2026-11-11).
  • Sold by 6 providers (as of 2026-11-11): Amazon Bedrock $2.00 in / $6.00 out · xAI $2.00 in / $6.00 out · xAI $2.00 in / $6.00 out · xAI $2.20 in / $6.60 out · xAI $4.00 in / $12.00 out · and 1 more. Every provider
  • Gecko Tests · Gecko Score 58 (rank 15): Who Are You B (Knows who made it) · World Map B (97.3% of the map right) · Knowledge Horizon C (Knows news up to Oct 2025) · Tokenizer Tax B (50% more tokens outside English).

How to cite · data as of 2026-11-11

Grok 4.7 · benchmarks, pricing and providers. BenchGecko, data as of 2026-11-11. https://benchgecko.ai/model/grok-4-7

Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP