Grok 4.20 Multi-Agent Beta

#305MultimodalProprietary

xAI

Grok 4.20 Multi-Agent Beta is a variant of xAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information across complex tasks. Reasoning effort behavior: - low / medium: 4 agents - high / xhigh: 16 agents

Model updates refreshed3d agoJul 1, 2026news + changelog

View Updates Subscribe

37.9

Quality Score

1250

Arena ELO

Undisclosed

Parameters

Context

Benchmarks and Competitive Signal

Structured

Use this section to answer one simple question first: how much outside evidence do we have that this model performs well? Structured benchmark scores appear first, then official provider evidence, then live arena signal.

This model has normalized benchmark rows, so scores here are directly comparable across benchmark sources.

TAU-Benchreasoning

17.6

SWE-Benchcoding