Claude 3.7 SonnetvsGrok 4.20 Beta

Claude 3.7 Sonnet
Grok 4.20 Beta
Benchmarks
Nonsense detection
BullshitBench v2
49%
56%Best
Coding
SWE-Bench Verified
62.3%
Abstract reasoning
ARC-AGI-2
53.3%
Science
GPQA Diamond
68%
Community preference
Arena Elo (Text)
1475
Overview
CompanyAnthropicSpaceXAI
Release dateFeb 24 2025Feb 17 2026
AccessProprietaryProprietary

Which is better: Claude 3.7 Sonnet or Grok 4.20 Beta?

Grok 4.20 Beta leads Claude 3.7 Sonnet on 1 of the 1 benchmark they both report (BullshitBench v2). Claude 3.7 Sonnet shipped 358 days before Grok 4.20 Beta, so benchmark comparisons should account for the intervening progress.

Published specifications for these two models are limited — see each model page for the latest details.

On BullshitBench v2, Grok 4.20 Beta leads at 56% vs Claude 3.7 Sonnet at 49%.

Frequently asked questions

Claude 3.7 Sonnet was released by Anthropic on Feb 24 2025.

Grok 4.20 Beta was released by SpaceXAI on Feb 17 2026.

Other comparisons