NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/Grok 4.3
xAI logo

Grok 4.3

by xAI · Released Apr 2026

Multimodal1M Context
61.7
avg score
Rank #76
Compare
Better than 76% of all models
Context
1.0M tokens (~500 books)
Input $/1M
$1.25
Output $/1M
$2.50
Type
multimodal
License
Proprietary
Benchmarks
23 tested
Data as of
About

Grok 4.3 is a reasoning model from xAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...

Tested on 23 benchmarks · BenchGecko score 61.7. Top scores: Chatbot Arena Elo — Overall (1441.4%), Chatbot Arena Elo — Coding (1356.6%), OTIS Mock AIME 2024-2025 (93.3%).

Looking for similar performance at lower cost?
Qwen3.6 27B scores 62.2 (101% as good) at $0.32/1M input · 74% cheaper
Capabilities
coding
56.6
#62 globally
reasoning
63.3
#53 globally
math
58.8
#90 globally
knowledge
51.5
#114 globally
language
68.2
#85 globally
speed
34.6
#77 globally
general
46.8
#40 globally
Benchmark Scores
Compare All
Tested on 23 benchmarks · Ranked across 8 categories
Score Distribution (all 312 models)
0255075100
▲ You are here
codingCompare coding →
LiveBench — Coding

Regularly refreshed coding problems that avoid data contamination. New problems added monthly to prevent memorization.

69.9·
LiveBench — Agentic Coding

LiveBench coding tasks that require multi-step reasoning and tool use. Tests planning and execution of complex coding workflows.

50.0·
WeirdML

Unusual and adversarial machine learning challenges. Tests robustness of reasoning about edge cases in ML systems.

49.9·
reasoningCompare reasoning →
LiveBench — Reasoning

Regularly refreshed reasoning problems testing logical deduction, spatial reasoning, and analytical thinking.

70.8·
LiveBench — Data Analysis

Fresh data analysis tasks testing ability to interpret tables, charts, and statistical data.

55.8·
mathCompare math →
OTIS Mock AIME 2024-2025

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

93.3·
LiveBench — Mathematics

Regularly updated math problems that test numerical reasoning, algebra, calculus, and combinatorics.

84.3·
FrontierMath-Tiers-1-3-v2-Private
42.8·
Quick compare:vs PaLM 2-SMicrosoft logovs phi-3-mini 3.8BMicrosoft logovs WizardLM-2 8x22B
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Model Family · xAI Grok 4.3
Apr 2026
61.7
$1.25/M in1.0Mctx23 benchmarks
Apr 2026
$1.00/M in(-0.25)1.0Mctx
See the full Grok 4.3 family →
Recently Happened
Grok 4.3 added
May 1, 2026
Similar Models
PaLM 2-S
Unknown
61.7n/a
Microsoft logo
phi-3-mini 3.8B
Microsoft
61.5n/a
Microsoft logo
WizardLM-2 8x22B
Microsoft
61.4$0.62/1M
Links
Info
xAIPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@xAI
BenchGecko API
grok-4-3
Specifications
  • Typemultimodal
  • Context1.0M tokens (~500 books)
  • ReleasedApr 2026
  • LicenseProprietary
  • StatusActive
  • Cost / Message~$0.005
Available On
xAI logoxAI$1.25
Categories
codingreasoningmathknowledgelanguagespeedgeneral
Learn More
context-windowtransformertokens
Share & Export
Tweet
Related Models
PaLM 2-S
61.7
Microsoft logophi-3-mini 3.8B
61.5
Microsoft logoWizardLM-2 8x22B
61.4
Google DeepMind logoGemini 3.5 Flash
61.3
Grok 4.3 is a proprietary multimodal AI model by xAI, released in April 2026. It has an average benchmark score of 61.7. Context window: 1M tokens.

Related Models

PaLM 2-S · Unknownphi-3-mini 3.8B · MicrosoftWizardLM-2 8x22B · MicrosoftGemini 3.5 Flash · Google DeepMindQwen3.6 27B · Alibaba Qwen

Benchmarks

Chatbot Arena Elo — OverallChatbot Arena Elo — CodingOTIS Mock AIME 2024-2025GPQA diamondDtbench

Related Pages

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

Key facts · as of 2026-10-05

  • Grok 4.3 by xAI. BenchGecko score 61.7, rank 76 of 312 scored models (normalized average of public benchmark scores).
  • List price $1.25 input · $2.50 output per 1M tokens (as of 2026-10-05).
  • Sold by 4 providers (as of 2026-10-05): xAI $1.25 in / $2.50 out · xAI $1.25 in / $2.50 out · xAI $2.50 in / $5.00 out · xAI $2.50 in / $5.00 out. Every provider
  • Gecko Tests: Who Are You B (Knows who made it) · Tokenizer Tax B (44% more tokens outside English).

How to cite · data as of 2026-10-05

Grok 4.3 · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/grok-4-3

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