RankingIA v0.6.1
EN

GPT-5.5

OpenAI

76.0#23 of 427 overall
Input / output
US$ 5,00 / US$ 30,00
US$ per 1M tokens
Context
1.1M
tokens
Release
04/24/2026
release date
Weights
Closed
 
Speed
0 tok/s
first token in 0.00 s

Family history

The 8 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-405/28/2023——1206
GPT-4.502/27/2025——1417
GPT-4.104/14/202535.8#2981383
GPT-508/07/202550.6#1421406
GPT-5.111/13/202559.9#801443
GPT-5.212/10/202555.2#1031416
GPT-5.403/05/202673.8#311469
GPT-5.504/24/202676.0#231472

Scores by source

Scores by sourcepercentile = % of ranked models it beats
MetricValuePercentileSource
Arena text (Elo) weight 2 1472 87% LMArena
Arena WebDev (Elo) weight 1 1512 57% LMArena
Arena vision (Elo) weight 0.5 1297 85% LMArena
Humanity's Last Exam weight 1 45.8 95% Artificial Analysis
Terminal-Bench weight 1 14.6 77% Artificial Analysis
GPQA Diamond 93.5 98% Artificial Analysis
Long-context reasoning 84.3 99% Artificial Analysis

By category

CategoryScoreRankMetrics
Agentic63.5#26Terminal-Bench
Coding53.5#47Arena WebDev (Elo)
Reasoning81.0#9Humanity's Last Exam, GPQA Diamond
Research74.5#7Long-context reasoning
Design53.5#46Arena WebDev (Elo)
Chat68.3#27Arena text (Elo)
Vision67.4#17Arena 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