name = "Grok 4.3"
description = "xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk"
family = "grok"
release_date = "2026-04-17"
last_updated = "2026-04-17"
attachment = true
reasoning = true
temperature = true
tool_call = true
structured_output = true
open_weights = false

[limit]
context = 1_000_000
output = 30_000

[modalities]
input = ["text", "image", "pdf"]
output = ["text"]

[[benchmarks]]
name = "Artificial Analysis Intelligence Index"
score = 53
metric = "index score"
version = "4.0"
source = "https://artificialanalysis.ai/articles/xai-launches-grok-4-3-with-improved-agentic-performance-and-lower-pricing"
date = "2026-04-30"

[[benchmarks]]
name = "GDPval-AA"
score = 1500
metric = "Elo"
source = "https://artificialanalysis.ai/articles/xai-launches-grok-4-3-with-improved-agentic-performance-and-lower-pricing"
date = "2026-04-30"

[[benchmarks]]
name = "τ²-Bench Telecom"
score = 98
metric = "success rate"
source = "https://artificialanalysis.ai/articles/xai-launches-grok-4-3-with-improved-agentic-performance-and-lower-pricing"
date = "2026-04-30"

[[benchmarks]]
name = "IFBench"
score = 81
metric = "accuracy"
source = "https://artificialanalysis.ai/articles/xai-launches-grok-4-3-with-improved-agentic-performance-and-lower-pricing"
date = "2026-04-30"