Skip to main content

GPT-5.5 (Xhigh)

OpenAIGPTProprietary

Description

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.

Release Date
2026-04-23
Parameters
—
Context Length
1.1M
Modalities
image, pdf, text

Capability Radar

70
general
70
coding
60
reasoning
77
scienceest.
80
agents
85
multimodal

Science is estimated from LLM Stats science scores or reasoning when no dedicated science benchmarks are available.

Rankings

Domain#RankScoreSource
Agentic Capability56
50.0
LS
Code Ranking23
85.0
LB
Math Reasoning8
96.0
LB
Multimodal Ranking28
61.0
LS
Reasoning15
90.0
LB

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

Agents

BixBench80.5%SR
Finance Agent60.0%SR
Toolathlon55.6%SR
OfficeQA Pro54.1%SR
Finance Agent v251.8%
GeneBench25.0%SR

Code

CyberGym81.8%SR
FrontierSWE73.0%
DeepSWE 1.167.0%

Communication

Tau2 Telecom98.0%SR

General

GDPval-MM84.9%SR

Legal

Legal Agent Benchmark2.1%

Long Context

MRCR v2 (8-needle)74.0%SR

Math

LiveBench80.7%
FrontierMath35.4%SR

Multimodal

OSWorld-Verified78.7%SR

Reasoning

ARC-AGI95.0%SR
GPQANYU + Cohere + Anthropic (2023)93.6%SR
ARC-AGI v285.0%SR
BrowseCompOpenAI (2025)84.4%SR
Terminal-Bench 2.0Stanford × Laude Institute (2026)82.7%SR
MCP Atlas75.3%SR
SWE-Bench ProPrinceton NLP (2024)58.6%SR
Graphwalks parents >128k58.5%SR
Humanity's Last Exam52.2%SR
Graphwalks BFS >128k45.4%SR
FrontierCode 1.143.0%

Vision

MMMU-Pro83.2%SR

AA Evaluation Indices

(Artificial Analysis)

No AA evaluation data available

LLM Stats Category Scores

(LLM Stats (zeroeval))
Communication
100
Physics
90
Biology
90
Chemistry
90
Multimodal
80
Safety
80
Search
80
Tool Calling
80
Vision
80
Spatial Reasoning
70
Finance
70
General
70
Code
70
Long Context
60
Math
60
Reasoning
60
Agents
60
Science
20
Legal
0

Pricing

Input Price$5 / 1M tokens
Output Price$30 / 1M tokens
Blended Price (3:1)$11.25 / 1M tokens
Cache Read Price$0.5 / 1M tokens

Speed

Tokens/sec77.5
Time to First Token38.88s
Time to Answer38.88s

Provider Price Ranking

Provider Price Ranking

4 providers

Cheapest: KunavoMost Expensive: Neon
ProviderInputOutput
1KunavoCheapest
$2
$12
2OpenAIPRIMARY
$5
$30
3FrogBot
$5
$30
4Neon
$5
$30

Compare pricing across different API providers for this model.

External Sources