Name: Grok 4.20
Author: xAI

Grok 4.20

xAI · 2026-03-10

Grok 4.20 is xAI's high-performance model released in March 2026, with a 1 million-token context window and agentic tool-calling capabilities. The current xAI docs identify the reasoning model as grok-4.20-0309-reasoning and list aliases including grok-4.20, while xAI's release notes state Grok 4.20 and Grok 4.20 Multi-agent went live on March 10, 2026.

Benchmark scores

Benchmark	Score
A-Fantasia	73.0
A-Fantasia Backwards Spelling	82.0
A-Fantasia Chess	63.0
A-Fantasia Cube Rotation	74.0
AA-LCR	59.0
AA-Omniscience Index	15.3
Agent Red Teaming k=100 (CAIS)	84.6
AIME 2024 (avg@8)	98.8
AIME 2024-2025	96.5
AIME 2025 (avg@8)	94.2
ALE-Bench	1388
Antidote: Everyday Edition	1000
APEX-Agents-AA	14.2
ARC-AGI-1	89.5
ARC-AGI-3 (Semi-Private)	0.1
Artificial Analysis Intelligence Index	37.0
Artificial Analysis Omniscience Accuracy	28.9
Artificial Analysis Omniscience Hallucination Rate	16.7
Bench to the Future 2	0.2
Bench to the Future 2 — Calibration Error	0.0
Bench to the Future 2 — Refinement	0.0
BioSecBench-Refusal	3.1
BioSecBench-Surveillance	13.7
BioTIER Refusal	71.6
Blueprint-Bench 2	0.0
BullshitBench v2 Leaderboard	67.0
BuseyBench SVG	3.8
Buyout Game Bradley-Terry Rating	1549
CadQueryEval	24.0
CadQueryEval — Bounding Box	36.0