Skip to main content
BenchLM
xAI logo

xAI

Data verified
This page groups canonical xAI model families and applies the same public scoring lane used by the main leaderboard.
Model count
18
Best model
69.19/100
Grok 4.6
Avg. top 3
64.7/100
Latest release
September 2026
Public-ranked
10
Supported
4

Score trend

0255075100Apr 2025Jul 2025Oct 2025Jan 2026Apr 2026Sep 2026xAI

xAI's average score across its top 3 ranked models, cumulative through each release month.

Provider models

ContextPricePublic score
Grok 4.6Superseded500K$2.00 / $6.005842.75s69.19Supported
Grok 4.5Superseded500K$2.00 / $6.005310.94s65.27Supported
Grok 4.20Established2M$1.25 / $2.5010522.67s59.66Estimated
Grok 4.3Superseded1M$1.25 / $2.5010421.80s54.73Supported
Grok 4Established128KN/A5415.60s52.72Supported
Grok 3 [Beta]Established128KN/AN/AN/A45.04Estimated
Grok 3 MiniEstablished128K$0.30 / $0.507529.60s43.64Estimated
Grok 4 Fast (Reasoning)Established2MN/AN/AN/A42.43Estimated
Grok 4.1 FastEstablished1M$0.20 / $0.501380.54s36.33Estimated
Grok Code Fast 1Established256K$0.20 / $1.501722.81s32.05Estimated
Grok 4.1Superseded1MN/AN/AN/A—
Grok 4.7Current500K$2.00 / $6.00390.87s—
Grok Build 0.1Current256K$1.00 / $2.00N/AN/A—
Grok RealtimeTrackedN/AN/AN/AN/A—
Grok TTSCurrentN/AN/AN/AN/A—
Grok Voice Think Fast 1.0TrackedN/AN/AN/AN/A—
Grok Voice Think Fast 2.0TrackedN/AN/AN/AN/A—
Grok Voice Transcribe 2.0CurrentN/AN/AN/AN/A—
Radar

xAI release history

Full release history

Radar confirmed these at the source. Use xAI in your work? Explore Radar to follow supported changes and choose your alerts.

Compare xAI models