Grok 4.7 vs Grok Build 0.1 vs Grok 4.3

Best cell per row highlighted. Null means undisclosed — never counted as zero.

xAI
Grok 4.7GA
8.2
AI Panel
xAI
Grok Build 0.1GA
6.7
AI Panel
xAI
Grok 4.3GA
7.7
AI Panel

Identity & lifecycle

ProviderxAIxAIxAI
Family / tierGrok 4 · FlagshipGrok Build · CoderGrok 4 · Flagship
StatusGAGAGA
Released2026-09-212026-05-202026-04-30
Knowledge cutoff2026-052024-112025-12

Architecture & context

Context window500K256K1M
Max output tokens—256K—
Input modalitiestext, imagetext, imagetext, image, video
Reasoning modealwaysalwaysalways
Open weightsNoNoNo

Pricing (per Mtok)

Input$2$1$1.25
Output$6$2$2.5
Cached input$0.5$0.2$0.2
Batch input——$1
Free tierYesNoYes

Speed

Output speed (tok/s)——181.5
Time to first token (s)——19.69
Latency tiermediumslowslow

Trust & deployment

Trains on inputsNoNoNo
LicenseProprietaryProprietaryProprietary
Clouds——Azure AI Foundry
ComplianceSOC2SOC2SOC2

AI Panel scoring

Unified score8.26.77.7
Decision Maker86.57.5
Domain Strategist8.56.58
Finance Lead97.58.5
Domain Practitioner8.577.5
Power User86.57.5
Skeptic766.5
Value score8.87.58.5

Benchmarks

GPQA Diamond——90
SWE-bench Verified—70.8—
IFEval——81
TAU-bench——98
LMArena Elo——1443
LMArena Coding Elo——1488

Scores link to their sources. Missing cells mean the vendor hasn't disclosed a result — honesty over padding.