Private AI

Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Search
 
 
 
 
All conversations

Create

Chat
Studio

Explore

Models
Pricing
AI Apps
Blog

Library

Gallery
Workspace
Usage & billing
API
Suggestions and bugs
Use cases

|

Terms

|

Privacy

|

Refunds
Usage & billing
Teams
Referrals
Presets
Settings
FAQPress & mediaBrand assetsBenchmarksNano RPCEarn crypto
  1. Models
  2. Text
  3. xAI

Grok Latest

Compatibility alias that routes to the newest Grok model. Currently routes to Grok 4.7. Content policy rejections can still be charged: SpaceXAI may pass through a $0.05 moderation-failure fee, or a $0.055 usage-guidelines violation fee, depending on which rejection upstream returns.

  • Reasoning
  • Vision
  • Tool Calling
  • Structured Output

Added May 3, 2026

Pricing

Auto routing · per 1M tokens
Input
$2.00
Output
$6.00
Cache read
$0.50
Compare provider prices

Specifications

Context window
500K
Max output
500K

Benchmarks

Sourced from LMArena.

Arena Score

1443.3

Overall Rank

#92 / 421

Votes

22,219

Confidence Interval

1438.0 - 1448.6

Category Scores

Coding

#93 / 416

4,876 votes

1492.5

Math

#86 / 404

1,088 votes

1447.2

Longer Query

#86 / 399

9,380 votes

1453.8

Creative Writing

#85 / 419

5,096 votes

1421.4

Instruction Following

#89 / 421

7,408 votes

1435.4

Hard Prompts

#89 / 421

13,700 votes

1465.5

Additional Categories
22

Polish

#52 / 243

310 votes

1468.8

Industry Mathematical

#67 / 402

1,230 votes

1468.8

Chinese

#72 / 395

1,749 votes

1494.7

French

#73 / 301

787 votes

1474.5

Korean

#73 / 289

314 votes

1412.6

Industry Legal And Government

#78 / 393

1,768 votes

1462.7

Japanese

#79 / 288

383 votes

1414.7

Expert

#81 / 371

2,106 votes

1478.0

Industry Entertainment And Sports And Media

#84 / 419

5,718 votes

1420.1

Industry Writing And Literature And Language

#85 / 420

6,448 votes

1428.7

Industry Life And Physical And Social Science

#86 / 419

3,651 votes

1467.8

English

#89 / 421

8,485 votes

1453.8

Hard Prompts English

#89 / 419

5,325 votes

1471.7

Spanish

#91 / 304

825 votes

1441.4

Exclude Ties

#93 / 421

16,444 votes

1443.2

Non English

#93 / 421

13,702 votes

1430.7

Russian

#94 / 385

3,234 votes

1439.5

Industry Software And It Services

#97 / 421

7,746 votes

1480.7

Industry Medicine And Healthcare

#100 / 391

1,550 votes

1457.6

German

#109 / 320

342 votes

1427.3

Industry Business And Management And Financial Operations

#112 / 414

3,812 votes

1438.1

Multi Turn

#115 / 419

3,349 votes

1434.9

Published 2026-11-11 · Matched as Grok 4.7 (xHigh) · CC BY 4.0

LMArena Dataset

Leaderboard results

These leaderboards tested Grok 4.7, another version of this model.

BenchmarkScoreRank on NanoGPT
Epoch AI Benchmarking Hub

Epoch AI data, CC BY 4.0 · Updated Nov 13, 2026

Epoch Capabilities Index

156.2

#37 of 115

FrontierMath v2 (Tiers 1–3)

53.0%

#53 of 83

GPQA Diamond

92.7%

#24 of 119

SimpleQA Verified

56.0%

#23 of 82

FrontierMath v2 (Tier 4)

17.1%

#54 of 67

OTIS Mock AIME 2024–2025

98.1%

#30 of 121

MirrorCode

54.4%

#14 of 39

Chess Puzzles

41.0%

#37 of 82

Mystery Game Puzzles

29.0%

#35 of 77

EQ-Bench

EQ-Bench data, MIT · Updated Nov 13, 2026

Creative Writing v3

2012

#9 of 96

Longform Writing

83.0

#5 of 97

UGI Leaderboard

UGI Leaderboard data, Apache-2.0 · Updated Oct 16, 2026

UGI Score

33.9

#90 of 149

UGI Willingness

3.8

#65 of 149

UGI Writing

54.1

#50 of 149

Filtered and ranked to models on NanoGPT.

Providers

Auto
Auto (ZDR)
$2.00$6.00$0.50N/AN/A
>200k$4.00$12.00$1.00
Auto
Auto (Anonymized)
$2.00$6.00$0.50N/AN/A
>200k$4.00$12.00$1.00

Related text models

Compare Grok Latest with similar models from the same provider or model family.

Grok 4.7

x-ai/grok-4.7

Grok 4.7 is SpaceXAI's flagship reasoning model for coding, long-running agentic tasks, and knowledge work. It supports text, image, and file inputs with tool calling and structured outputs. Reasoning is always active, and requests above 200k input tokens use higher long-context rates. Content policy rejections can still be charged: SpaceXAI may pass through a $0.05 moderation-failure fee, or a $0.055 usage-guidelines violation fee, depending on which rejection upstream returns.

Grok 4.6

x-ai/grok-4.6

Grok 4.6 is SpaceXAI's frontier reasoning model for coding, knowledge work, and STEM. It supports text, image, and file inputs with tool calling and structured outputs. Reasoning is always active, and requests above 200k input tokens use higher long-context rates. Content policy rejections can still be charged: SpaceXAI may pass through a $0.05 moderation-failure fee, or a $0.055 usage-guidelines violation fee, depending on which rejection upstream returns.

Grok 4.5

x-ai/grok-4.5

Grok 4.5 is SpaceXAI's frontier reasoning model for coding, knowledge work, and STEM. It supports text, image, and file inputs with tool calling and structured outputs. Reasoning is always active. Content policy rejections can still be charged: SpaceXAI may pass through a $0.05 moderation-failure fee, or a $0.055 usage-guidelines violation fee, depending on which rejection upstream returns.

Grok Build 0.1

x-ai/grok-build-0.1

Grok Build 0.1 is SpaceXAI's fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding agents, tool use, and multi-step development tasks. Currently in early access. Content policy rejections can still be charged: SpaceXAI may pass through a $0.05 moderation-failure fee, or a $0.055 usage-guidelines violation fee, depending on which rejection upstream returns.

Grok 4.3

x-ai/grok-4.3

Grok 4.3 is SpaceXAI's reasoning model for text and image inputs, built for agentic workflows, instruction following, factual accuracy, long-document analysis, and deep research. Reasoning is always active and requests above 200k total tokens are charged at the higher long-context rate. Content policy rejections can still be charged: SpaceXAI may pass through a $0.05 moderation-failure fee, or a $0.055 usage-guidelines violation fee, depending on which rejection upstream returns.

Grok 4.20

x-ai/grok-4.20

SpaceXAI's Grok 4.20 flagship release with tool calling, multimodal input support, and a 2M-token context window. Content policy rejections can still be charged: SpaceXAI may pass through a $0.05 moderation-failure fee, or a $0.055 usage-guidelines violation fee, depending on which rejection upstream returns.