Enterprise DNAEnterprise DNA

Model comparison

Grok 4.20 vs Grok 4.3

Price history, scores and specs for both models, line by line. Every value shows where it came from and when we last confirmed it.

xAI logo

xAI

Grok 4.20

Grok 4.20 is a reasoning model from xAI with industry-leading speed and agentic tool calling capabilities.

15 checked values

View model
xAI logo

xAI

Grok 4.3

Grok 4.3 is a reasoning model from xAI.

20 checked values

View model

Quick take

Where each one leads

  • Grok 4.20 reads more at once: 2,000,000 tokens, against 1,000,000 tokens.
  • Grok 4.20 scores higher on the Artificial Analysis Intelligence Index: 25.7 to 24.9.
  • More people run Grok 4.3 through OpenRouter than Grok 4.20 right now.

Each line comes from a checked value in the tables below. Pick on your workload: price and usage matter for high volume, context and scores for long documents and agent loops.

Price history

Prices side by side, day by day

Input price history
$0$0.688$1.383 Sept 202610 Nov 2026
Output price history
$0$1.38$2.753 Sept 202610 Nov 2026

Prices are the listed OpenRouter base rates in US dollars. A day we could not confirm is left out of the line, never filled in.

Price

What each one costs now

Grok 4.20 vs Grok 4.3: What each one costs now
MeasureGrok 4.20Grok 4.3
Input price$1.25 per million tokensChecked OpenRouter models API$1.25 per million tokensChecked OpenRouter models API
Output price$2.50 per million tokensChecked OpenRouter models API$2.50 per million tokensChecked OpenRouter models API

Scores

Benchmarks, with source and date

Grok 4.20 vs Grok 4.3: Benchmarks, with source and date
MeasureGrok 4.20Grok 4.3
Artificial Analysis Intelligence Index25.7 LeadsChecked Artificial Analysis via OpenRouter24.9Checked Artificial Analysis via OpenRouter
Artificial Analysis Coding IndexNot checked yet42.2Checked Artificial Analysis via OpenRouter
Artificial Analysis Agentic IndexNot checked yet15.5Checked Artificial Analysis via OpenRouter
LMArena text rating (Elo)Not checked yet1,397Checked LMArena (CC-BY-4.0), published 2026-11-09
LMArena web development rating (Elo)Not checked yet1,357Checked LMArena (CC-BY-4.0), published 2026-11-09
LMArena vision rating (Elo)Not checked yet1,229Checked LMArena (CC-BY-4.0), published 2026-11-09
Design Arena rating (Elo)1,226 LeadsChecked Design Arena via OpenRouter1,192Checked Design Arena via OpenRouter

Specs

Context, modalities and tool use

Grok 4.20 vs Grok 4.3: Context, modalities and tool use
MeasureGrok 4.20Grok 4.3
Context window2,000,000 tokens LeadsChecked OpenRouter models API1,000,000 tokensChecked OpenRouter models API
ReadsText, Images, FilesChecked OpenRouter models APIText, Images, FilesChecked OpenRouter models API
WritesTextChecked OpenRouter models APITextChecked OpenRouter models API
Tool callingYesChecked OpenRouter models APIYesChecked OpenRouter models API
Reasoning modeYesChecked OpenRouter models APIYesChecked OpenRouter models API
Open weightsNoChecked OpenRouter models APINoChecked OpenRouter models API
Listed since31 Mar 2026Checked OpenRouter models API30 Apr 2026Checked OpenRouter models API

Usage

How much each one is used

Grok 4.20 vs Grok 4.3: How much each one is used
MeasureGrok 4.20Grok 4.3
Tokens served on OpenRouter in a day3.1B (for 10 Nov 2026)Checked OpenRouter model activity (748 of 748 series)6.5B Leads (for 10 Nov 2026)Checked OpenRouter model activity (748 of 748 series)
Requests on OpenRouter in a day642K (for 10 Nov 2026)Checked OpenRouter model activity (748 of 748 series)1.3M Leads (for 10 Nov 2026)Checked OpenRouter model activity (748 of 748 series)
Tool calls on OpenRouter in a day40.2K (for 10 Nov 2026)Checked OpenRouter model activity (748 of 748 series)88.5K Leads (for 10 Nov 2026)Checked OpenRouter model activity (748 of 748 series)
Token usage, last 7 daysUp 3% on the week before (for 10 Nov 2026)Checked OpenRouter model activity (748 of 748 series)Up 4% on the week before Leads (for 10 Nov 2026)Checked OpenRouter model activity (748 of 748 series)
Tokens served a day on OpenRouter
1.8B7.7B13.5B19 Sept 202610 Nov 2026

How this works

One link, either order

This link stays the same whichever order you name the two models in, so you can share it as it is. A line appears only when at least one model has a value we confirmed from a source; values we have not confirmed are left out, never guessed. To add a third record of any type, use the open comparison. Read how we check facts.