RankingIA v0.6.1
EN

Grok 4.20

xAI

62.7#71 of 427 overall
Input / output
US$ 1,25 / US$ 2,50
US$ per 1M tokens
Context
2M
tokens
Release
03/31/2026
release date
Weights
Closed
 
Speed
0 tok/s
first token in 0.00 s

Family history

The 11 versions of this family, from first to newest, by release date. Click a point to open that version.

See the data as a table
ModelReleasedScoreRankAA Intel.Elo Arena
Grok 212/12/202420.5#401—1305
Grok 302/19/202545.6#192—1425
Grok 407/10/202554.0#111—1411
Grok 4.1————1436
Grok 4.2003/31/202662.7#71—1451
Grok 4.20 0309 v204/07/202666.8#55——
Grok 4.304/30/202644.0#206—1397
Grok Latest07/08/202634.5#308——
Grok 4.507/08/202672.9#32—1448
Grok 4.608/12/202665.3#60—1429
Grok 4.709/21/202666.4#5735.01398

Scores by source

Scores by sourcepercentile = % of ranked models it beats
MetricValuePercentileSource
Arena text (Elo) weight 2 1451 79% LMArena
Arena WebDev (Elo) weight 1 1375 26% LMArena
Arena vision (Elo) weight 0.5 1262 59% LMArena
Humanity's Last Exam weight 1 32.4 82% Artificial Analysis
GPQA Diamond 88.5 86% Artificial Analysis
Long-context reasoning 67.7 57% Artificial Analysis

By category

CategoryScoreRankMetrics
Coding38.0#86Arena WebDev (Elo)
Reasoning72.6#58Humanity's Last Exam, GPQA Diamond
Research53.7#147Long-context reasoning
Design38.0#86Arena WebDev (Elo)
Chat64.6#42Arena text (Elo)
Vision54.3#44Arena vision (Elo)

History

RankingIA score on each collection day (hover to see the rank).

Daily collection started on 10/30/2026. The chart appears from the second day the model is ranked.

Compare with other models

At the sources