Grok 4.3

xAI

Verified against Artificial Analysis · Jul 13, 2026

Capability

percentile index

Price /M

$1.25 / $2.5

in / out

Context

tokens

Avg score

64.8

7 benchmarks

AA Intelligence

37.6

index

Speed

152 tok/s

TTFT 34s

Released

Apr 30, 2026

About

Grok 4.3 is a proprietary model in the Grok family from xAI. Benchmarked on 7 evals, averaging 64.8.

Benchmark scores · 7

avg 64.8 — higher is better

τ²-benchartificial-analysis · 2026-07

97.7

GPQA Diamondartificial-analysis · 2026-07

90.1

IFBenchartificial-analysis · 2026-07

81.3

AA Long-Context Reasoningartificial-analysis · 2026-07

64.3

SciCodeartificial-analysis · 2026-07

47.3

Terminal-Bench Hardartificial-analysis · 2026-07

37.9

Humanity's Last Examartificial-analysis · 2026-07

Details

PublisherxAI

FamilyGrok

Parameters—

License—

WeightsClosed

ReleasedApr 30, 2026

Performance & price

Output speed152 tok/s

Latency (TTFT)34s

Price in / out$1.25 / $2.5 per 1M

Blended price$1.56 / 1M

Coding index42.2

Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →

History

full ledger →

Capability over time

Append-only ledger — every observed change to this model's numbers.

API providers

Artificial Analysis$2.5/M