Back to the index
xAI · Grok
No. 16

Grok 4.3

xAI's flagship: strong math reasoning and real-time knowledge at aggressive pricing.

BalancedClosed weightsText, Image, Video, Pdf
Field notes
Context window
1Mtokens
Max output
66Ktokens
Input price
$1.25/ 1M tokens
Output price
$2.50/ 1M tokens
Cached input
$0.20/ 1M tokens
Modalities
Text, Image, Video, Pdf
Knowledge cutoff
Dec 2025
Released
Apr 2026
Approx. speed
~127 tok/s
Overview

What this model is

Grok 4.3 is xAI's current flagship, a large reasoning model with a 1M-token context window and native access to real-time X/web data. It benchmarks near the top on math and science and is a genuinely strong general model. In practice its long-horizon agentic coding is less consistent than the Claude/GPT frontier — it can be verbose, over-confident, and drift on multi-step tool use.

Strengths

  • Excellent math and scientific reasoning
  • Real-time knowledge via X/web integration
  • Native video input (new in 4.3)
  • Large 1M-token context window
  • Competitive pricing for a flagship

Trade-offs

  • Long agentic coding less reliable than Claude/GPT
  • Verbose and occasionally over-confident output
  • Tool-use consistency lags the frontier
  • Tone and moderation can be polarizing

Best for

  • Math and STEM reasoning
  • Real-time research and current events
  • General chat and analysis
  • Long-context document work

Not ideal for

  • Unsupervised long-horizon agentic coding
  • Safety-critical automated workflows
Capabilities

Capability profile

Normalized 0–100 scores, comparable across the whole catalog.

Reasoning84Coding74Math90Writing82Knowledge85Speed68Agentic73Vision80Multilingual82Long Context84
Reasoning
84
Coding
74
Math
90
Writing
82
Knowledge
85
Speed
68
Agentic
73
Vision
80
Multilingual
82
Long Context
84
Benchmarks

How it scores

Public benchmark results, with independent third-party results where available. Bars normalize percentages to 100 and Elo ratings to a 1500 ceiling.

Independent index
Artificial Analysis Intelligence Index
Composite of ~9–10 independent evals · Artificial Analysis
38/ 100
BenchmarkResult
Artificial Analysis Intelligence Indexindependent
GeneralArtificial Analysis
38%
SWE-bench Verifiedindependent
CodingSWE-bench
76.7%
τ-benchindependent
Agenticτ-bench
78.9%
AIME 2025
MathVendor-reported
100%
MMLU-Pro
KnowledgeVendor-reported
91.2%
Terminal-Bench Hardindependent
AgenticArtificial Analysis
37.9%
LMArena Eloindependent
GeneralLMArena
1496Elo
Alternatives

Comparable models

Models in a roughly similar class — worth weighing against this one.