RankingIA v0.6.1
EN

GPT-5.3-Codex

OpenAI

58.9#85 of 427 overall
Input / output
US$ 1,75 / US$ 14,00
US$ per 1M tokens
Context
400K
tokens
Release
02/24/2026
release date
Weights
Closed
 
Speed
86 tok/s
first token in 50.88 s

Family history

The 4 versions of this family, from first to newest, by release date. Click a point to open that version.

See the data as a table
ModelReleasedScoreRankElo Arena
GPT-5 Codex09/23/202563.0#70—
GPT-5.1-Codex-Max12/04/202547.0#178—
GPT-5.2-Codex01/14/202650.8#141—
GPT-5.3-Codex02/24/202658.9#85—

Scores by source

Scores by sourcepercentile = % of ranked models it beats
MetricValuePercentileSource
Arena WebDev (Elo) weight 1 1407 35% LMArena
Humanity's Last Exam weight 1 42.5 91% Artificial Analysis
GPQA Diamond 91.5 94% Artificial Analysis
Long-context reasoning 83.3 97% Artificial Analysis

By category

CategoryScoreRankMetrics
Coding42.6#75Arena WebDev (Elo)
Reasoning78.4#21Humanity's Last Exam, GPQA Diamond
Research73.5#14Long-context reasoning
Design42.6#75Arena WebDev (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