llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeModelsGPT-5.5

OpenAI model product

GPT-5.5

GPT-5.5 is OpenAI's smartest model yet, designed for real work across agentic coding, computer use, knowledge work, and early scientific research. It matches GPT-5.4 per-token latency in real-world serving while reaching a much higher level of intelligence and using significantly fewer tokens to complete the same tasks. GPT-5.5 supports a 1M-token context window in the API and a 400K-token context window in Codex, with state-of-the-art results on Terminal-Bench 2.0, OSWorld-Verified, GDPval, FrontierMath, and CyberGym.

Updated Aug 10, 2026. Default version: GPT-5.5

Compare
LLMBoard score76.8GPT-5.5
Coverage100%8 benchmark families
Context window1.1MTokens
Official input price$5OpenAI API

On this page

  • Specification
  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Versions
  • About
  • Compare
  • Similar models
  • FAQ

Model specification

Structured fields from the published default version.

Version
GPT-5.5
Released
Apr 23, 2026
Knowledge cutoff
Dec 1, 2025
Parameters
N/A
Context window
1.1M
Max output
128K
Inputs
image, pdf, text
Outputs
text
Open weights
No
License
Proprietary

Capability profile

This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.

GPT-5.5 category scores

Benchmark results

Published benchmark records for the scored version GPT-5.5.

28 rows
Columns

Show columns

ARC-AGI0.917100.0%CAug 7, 2026
ARC-AGI v20.8116100.0%CAug 7, 2026
BixBench0.811100.0%CAug 7, 2026
GDPval-MM0.813100.0%CAug 7, 2026
Terminal-Bench 2.00.8149100.0%CAug 7, 2026
GeneBench0.3220.0%CAug 7, 2026
LiveBench0.823897.3%BAug 7, 2026
MMMU-Pro0.826598.4%CAug 7, 2026
CyberGym0.831180.0%CAug 7, 2026
Finance Agent0.64857.1%CAug 7, 2026
MRCR v2 (8-needle)0.742185.0%CAug 7, 2026
Finance Agent v20.552684.0%BAug 7, 2026
FrontierCode 1.10.451571.4%BAug 7, 2026
DeepSWE 1.10.761972.2%BAug 7, 2026
FrontierSWE0.761564.3%BAug 7, 2026
GPQA0.9623397.8%CAug 7, 2026
OfficeQA Pro0.56716.7%CAug 7, 2026
Tau2 Telecom1.063585.3%CAug 7, 2026
FrontierMath0.471762.5%CAug 7, 2026
Legal Agent Benchmark0.071350.0%BAug 7, 2026
Toolathlon0.673180.0%CAug 7, 2026
OSWorld-Verified0.882266.7%CAug 7, 2026
Graphwalks parents >128k0.691852.9%CAug 7, 2026
BrowseComp0.8125880.7%CAug 7, 2026
MCP Atlas0.8123062.1%CAug 7, 2026
Graphwalks BFS >128k0.5162228.6%CAug 7, 2026
Humanity's Last Exam0.5169283.5%CAug 7, 2026
SWE-Bench Pro0.6164465.1%CAug 7, 2026

Arena results

Preference and agent-evaluation signals from published Arena datasets.

100 rows
Columns

Show columns

text factualityjapanese21497.2389N/AAug 6, 2026
text factualitygerman41460.6390N/AAug 6, 2026
text factualitykorean41452.9471N/AAug 6, 2026
text factualitychinese51538.72,268N/AAug 6, 2026
text factualityfrench51516.51,578N/AAug 6, 2026
text factualityindustry business and management and financial operations51496.89,487N/AAug 6, 2026
text factualitymath61491.32,125N/AAug 6, 2026
text style controljapanese61497.4513N/AAug 6, 2026
textchinese81537.82,751N/AAug 6, 2026
textjapanese81490.5513N/AAug 6, 2026
text factualityexpert81523.34,480N/AAug 6, 2026
text factualityinstruction following81487.817,424N/AAug 6, 2026
visiondiagram81327.85,177N/AAug 6, 2026
vision style controldiagram81326.45,177N/AAug 6, 2026
vision style controlhomework81329.92,538N/AAug 6, 2026
documentoverall91480.317,286N/AJul 30, 2026
text factualityenglish91486.924,795N/AAug 6, 2026
text factualityhard prompts91508.735,252N/AAug 6, 2026
text factualityhard prompts english91512.116,410N/AAug 6, 2026
text factualityindustry life and physical and social science91505.67,667N/AAug 6, 2026
text factualityoverall101481.853,330N/AAug 6, 2026
text factualitylonger query101495.823,332N/AAug 6, 2026
text style controlmath101499.22,722N/AAug 6, 2026
text factualityindustry mathematical111483.02,295N/AAug 6, 2026
text factualityindustry software and it services111515.821,074N/AAug 6, 2026
text factualityrussian111491.54,461N/AAug 6, 2026
vision style controlenglish111283.57,886N/AAug 6, 2026
text factualityindustry legal and government121500.93,504N/AAug 6, 2026
text style controlchinese121531.72,751N/AAug 6, 2026
vision style controloverall121286.018,722N/AAug 6, 2026
text factualityexclude ties131486.940,759N/AAug 6, 2026
text factualityindustry writing and literature and language131469.612,640N/AAug 6, 2026
text factualitynon english131471.628,523N/AAug 6, 2026
text factualityspanish131461.61,174N/AAug 6, 2026
text factualityindustry entertainment and sports and media141455.911,442N/AAug 6, 2026
text factualitypolish141452.0586N/AAug 6, 2026
visionhomework141326.42,538N/AAug 6, 2026
vision style controlhumor141276.6642N/AAug 6, 2026
document style controloverall151475.517,286N/AJul 30, 2026
textexpert151501.85,361N/AAug 6, 2026
textindustry business and management and financial operations151473.410,608N/AAug 6, 2026
textinstruction following151473.118,057N/AAug 6, 2026
text factualitymulti turn151488.18,177N/AAug 6, 2026
visionoverall151296.318,722N/AAug 6, 2026
visionenglish151294.17,886N/AAug 6, 2026
visionhumor151286.5642N/AAug 6, 2026
vision style controlocr151298.613,517N/AAug 6, 2026
textfrench161489.02,005N/AAug 6, 2026
textmath161484.52,722N/AAug 6, 2026
text factualityindustry medicine and healthcare161498.53,187N/AAug 6, 2026
text style controlgerman161481.6813N/AAug 6, 2026
text style controlindustry business and management and financial operations161485.710,608N/AAug 6, 2026
text style controlindustry mathematical161497.92,912N/AAug 6, 2026
visionocr161306.013,517N/AAug 6, 2026
textgerman171470.1813N/AAug 6, 2026
textkorean171441.5889N/AAug 6, 2026
text style controlexpert171510.55,361N/AAug 6, 2026
text factualitycoding181525.114,523N/AAug 6, 2026
text style controlfrench181503.22,005N/AAug 6, 2026
visionchinese181349.41,077N/AAug 6, 2026
textindustry legal and government191479.94,321N/AAug 6, 2026
textindustry writing and literature and language191462.213,360N/AAug 6, 2026
textlonger query191478.523,890N/AAug 6, 2026
text factualitycreative writing191453.88,256N/AAug 6, 2026
text style controloverall201476.753,407N/AAug 6, 2026
text style controlindustry writing and literature and language201466.613,360N/AAug 6, 2026
texthard prompts211482.935,299N/AAug 6, 2026
textindustry mathematical211485.72,912N/AAug 6, 2026
text style controlinstruction following211473.918,057N/AAug 6, 2026
visioncreative writing vision211282.71,106N/AAug 6, 2026
textindustry life and physical and social science221481.58,694N/AAug 6, 2026
textrussian221473.15,369N/AAug 6, 2026
text style controlexclude ties221485.940,814N/AAug 6, 2026
text style controlindustry life and physical and social science221494.58,694N/AAug 6, 2026
vision style controlcreative writing vision221266.61,106N/AAug 6, 2026
textnon english231459.928,567N/AAug 6, 2026
text style controlenglish231481.024,839N/AAug 6, 2026
text style controlnon english231467.328,567N/AAug 6, 2026
textoverall241465.853,407N/AAug 6, 2026
textexclude ties241469.040,814N/AAug 6, 2026
textindustry entertainment and sports and media241442.312,179N/AAug 6, 2026
text style controlindustry legal and government241485.24,321N/AAug 6, 2026
vision style controlchinese241315.61,077N/AAug 6, 2026
textcreative writing251449.29,371N/AAug 6, 2026
text style controlhard prompts251496.535,299N/AAug 6, 2026
text style controllonger query251484.023,890N/AAug 6, 2026
text style controlrussian251479.85,369N/AAug 6, 2026
texthard prompts english261478.417,055N/AAug 6, 2026
textindustry software and it services261485.621,389N/AAug 6, 2026
textenglish271466.324,839N/AAug 6, 2026
textmulti turn281468.69,417N/AAug 6, 2026
text style controlhard prompts english281495.817,055N/AAug 6, 2026
text style controlmulti turn291480.79,417N/AAug 6, 2026
textspanish301458.81,569N/AAug 6, 2026
text style controlindustry software and it services301505.421,389N/AAug 6, 2026
textpolish321454.1972N/AAug 6, 2026
text style controlindustry entertainment and sports and media321443.812,179N/AAug 6, 2026
text style controlcreative writing331447.09,371N/AAug 6, 2026
text style controlindustry medicine and healthcare331485.63,947N/AAug 6, 2026
text style controlkorean331427.2889N/AAug 6, 2026

Pricing

Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.

Official API
$5 input, $30 output per 1M
Official provider
OpenAI
Lowest third-party
From $0.1875 input, $1.13 output per 1M via UnoRouter
Tracked offerings
17
16 rows
Columns

Show columns

UnoRoutergpt-5.5global$0.1875$1.131.1MAug 7, 2026
Xpersonagpt-5.5global$1.5$121.1MAug 7, 2026
Vivgridgpt-5.5global$5$301.1MAug 7, 2026
DaoXEgpt-5.5global$5$301.1MAug 7, 2026
LLM Gatewaygpt-5.5global$5$301.1MAug 7, 2026
OpenCode Zengpt-5.5global$5$301.1MAug 7, 2026
GitHub Copilotgpt-5.5global$5$301.1MAug 7, 2026
SAP AI Coregpt-5.5global$5$301.1MAug 7, 2026
Pioneergpt-5.5global$5$301.1MAug 7, 2026
AI-ROUTERgpt-5.5global$5$301.1MAug 7, 2026
Abacusgpt-5.5global$5$301MAug 7, 2026
Azure Cognitive Servicesgpt-5.5global$5$301.1MAug 7, 2026
Azuregpt-5.5global$5$301.1MAug 7, 2026
AIHubMixgpt-5.5global$5$301.1MAug 7, 2026
FreeModelgpt-5.5global$5$301.1MAug 7, 2026
OpenAIgpt-5.5global$5$301.1MAug 7, 2026

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

GPT-5.5 versions

All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.

1 rows
Columns

Show columns

GPT-5.5Apr 23, 202676.8N/A1.1M128KNoProprietary

What is GPT-5.5?

A concise description based on the published model registry.

GPT-5.5 is OpenAI's smartest model yet, designed for real work across agentic coding, computer use, knowledge work, and early scientific research. It matches GPT-5.4 per-token latency in real-world serving while reaching a much higher level of intelligence and using significantly fewer tokens to complete the same tasks. GPT-5.5 supports a 1M-token context window in the API and a 400K-token context window in Codex, with state-of-the-art results on Terminal-Bench 2.0, OSWorld-Verified, GDPval, FrontierMath, and CyberGym.

Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.

Data snapshot: 2026-08-07. Editorial model content is not available in the backend.

GPT-5.5 vs nearby models

Open a comparison with the three ranked models immediately above and below this model.

GPT-5.5vsClaude Opus 4.7GPT-5.5vsGemini 2.5 ProGPT-5.5vsGPT-5.6-LunaGPT-5.5vsGPT-5.4GPT-5.5vsDeepSeek-V3.2GPT-5.5vsQwen3.5 397B A17B

Models similar to GPT-5.5

Recommendations prioritize the same model type and family, then the closest published LLMBoard score.

#15+0.4
OP

GPT-5.6-Luna

OpenAI

77.2 LLMBoard

DetailsCompare
#17-1.1
OP

GPT-5.4

OpenAI

75.6 LLMBoard

DetailsCompare
#30-5.2
OP

GPT-5

OpenAI

71.6 LLMBoard

DetailsCompare
#34-7.6
OP

GPT-5.2

OpenAI

69.1 LLMBoard

DetailsCompare
#4+8.7
OP

GPT-5.6-Terra

OpenAI

85.4 LLMBoard

DetailsCompare
#45-13.8
OP

o1

OpenAI

63.0 LLMBoard

DetailsCompare

FAQ

Common questions about GPT-5.5.

When was GPT-5.5 released?

GPT-5.5's default version was released on Apr 23, 2026.

How much does GPT-5.5 cost?

GPT-5.5's official API price is $5 per million input tokens and $30 per million output tokens via OpenAI. The lowest tracked third-party offer starts at $0.1875 input and $1.13 output via UnoRouter.

Who created GPT-5.5?

GPT-5.5 is published under OpenAI in the model registry.

What is the context window for GPT-5.5?

The default version has a 1.1M token context window.

Is GPT-5.5 open weight?

No. The default version is not marked as having publicly available weights.

How many API providers offer GPT-5.5?

17 published provider offerings are linked to the default version.

What models should I compare GPT-5.5 with?

Nearby ranked alternatives include Claude Opus 4.7, Gemini 2.5 Pro, GPT-5.6-Luna.

Rankings

OverallCodingText ArenaPricing

Modalities

Image GenerationVideo GenerationSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai