Grok 4.3 vs Grok 4.7 vs Grok Build 0.1

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

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

Identity & lifecycle

ProviderxAIxAIxAI
Family / tierGrok 4 · FlagshipGrok 4 · FlagshipGrok Build · Coder
StatusGAGAGA
Released2026-04-302026-09-212026-05-20
Knowledge cutoff2025-122026-052024-11

Architecture & context

Context window1M500K256K
Max output tokens——256K
Input modalitiestext, image, videotext, imagetext, image
Reasoning modealwaysalwaysalways
Open weightsNoNoNo

Pricing (per Mtok)

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

Speed

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

Trust & deployment

Trains on inputsNoNoNo
LicenseProprietaryProprietaryProprietary
CloudsAzure AI Foundry——
ComplianceSOC2SOC2SOC2

AI Panel scoring

Unified score7.78.26.7
Decision Maker7.586.5
Domain Strategist88.56.5
Finance Lead8.597.5
Domain Practitioner7.58.57
Power User7.586.5
Skeptic6.576
Value score8.58.87.5

Benchmarks

GPQA Diamond90——
SWE-bench Verified——70.8
IFEval81——
TAU-bench98——
LMArena Elo1443——
LMArena Coding Elo1488——

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