Name: Grok 4.5
Author: xAI

Grok 4.5

xAI · 2026-07-08

Grok 4.5 is SpaceXAI's proprietary flagship model for coding, agentic tasks, and knowledge work, released July 8, 2026. It was trained alongside Cursor on curated coding, science, engineering, and mathematics data, with reinforcement learning across hundreds of thousands of multi-step software-engineering and technical tasks. The model supports text and image input, a 500,000-token context window, and configurable reasoning.

Benchmark scores

Benchmark	Score
AA-Briefcase Elo	1317
AA-LCR	67.7
AA-Omniscience Index	26.4
Agent Red Teaming k=100 (CAIS)	83.5
AHK-Eval	86.1
AHK-Eval Algorithms	66.7
AHK-Eval Data Structures	83.3
AHK-Eval Date and Time	83.3
AHK-Eval Easy	100.0
AHK-Eval Hard	75.0
AHK-Eval Hidden Cases	88.4
AHK-Eval Mid	83.3
AHK-Eval Numbers	100.0
AHK-Eval Parse Success	94.4
AHK-Eval Regex	100.0
AHK-Eval Strings	100.0
Aikido Known-CVE Detection (Pass@3 Union)	76.9
Aikido Known-CVE Detection (Single-Run Average)	66.7
ALE-Bench	1467
Antidote: Everyday Edition	977
APEX-Agents	34.2
ARC-AGI-1	87.2
ARC-AGI-2	52.6
ARC-AGI-3 (Semi-Private)	0.3
Arena Code WebDev — Brand & Marketing	1543
Arena Code WebDev — Consumer Product	1524
Arena Code WebDev — Content Creation Tools	1521
Arena Code WebDev — Data & Analytics	1514
Arena Code WebDev — Gaming	1583
Arena Code WebDev — HTML	1588