Passer au contenu principal
AITier

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.

Date de sortie
2026-04-23
Paramètres
—
Longueur du contexte
1.1M
Modalités
image, pdf, text

Radar de capacités

54
general
72
coding
93
reasoning
71
science
80
agents
85
multimodal

Classements

Domaine#RangScoreSource
Capacité agentique16
61.0
LS
Classement codage15
95.0
AA
Classement général10
91.0
AA
Science12
91.0
AA

Scores de benchmarks (LLM Stats)

(LLM Stats (zeroeval))

Agents

BrowseCompOpenAI (2025)84.4%Aut.
Terminal-Bench 2.0Stanford × Laude Institute (2026)82.7%Aut.
CyberGym81.8%Aut.
BixBench80.5%Aut.
OSWorld-Verified78.7%Aut.
MCP Atlas75.3%Aut.
FrontierSWE73.0%
DeepSWE 1.167.0%
Finance Agent60.0%Aut.
SWE-Bench ProPrinceton NLP (2024)58.6%Aut.
Toolathlon55.6%Aut.
OfficeQA Pro54.1%Aut.
Finance Agent v251.8%
FrontierCode 1.143.0%
GeneBench25.0%Aut.
Legal Agent Benchmark2.1%

Biology

GPQANYU + Cohere + Anthropic (2023)93.6%Aut.

Communication

Tau2 Telecom98.0%Aut.

Finance

GDPval-MM84.9%Aut.

General

MMMU-Pro83.2%Aut.
LiveBench80.7%
MRCR v2 (8-needle)74.0%Aut.

Long Context

Graphwalks parents >128k58.5%Aut.
Graphwalks BFS >128k45.4%Aut.

Math

Humanity's Last Exam52.2%Aut.
FrontierMath35.4%Aut.

Reasoning

ARC-AGI95.0%Aut.
ARC-AGI v285.0%Aut.

Indices d'évaluation AA

(Artificial Analysis)
Coding Index(Artificial Analysis)
74.9
Intelligence Index(Artificial Analysis)
56.3
Tau2(Sierra + U Toronto + Vector Institute (2025))
0.9
Gpqa(NYU + Cohere + Anthropic (2023))
0.9
Terminalbench V2 1
0.8
Lcr(Artificial Analysis)
0.8
Ifbench(Google Research (2023))
0.8
Terminalbench Hard(Stanford × Laude Institute (2026))
0.6
Scicode(UIUC + Argonne National Lab (2024))
0.6
Hle(Center for AI Safety + Scale AI (2025))
0.5
Tau Banking
0.4

Scores par catégorie LLM Stats

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

Tarification

Prix d'entrée$5 / 1M tokens
Prix de sortie$30 / 1M tokens
Prix mixte (3:1)$11.25 / 1M tokens
Prix de lecture cache$0.5 / 1M tokens

Vitesse

Tokens/sec0.0
Délai du premier token0.00s
Temps de réponse0.00s

Classement des Prix par Fournisseur

Classement des Prix par Fournisseur

3 fournisseurs

Moins cher: OpenAIPlus cher: Neon
FournisseurEntréeSortie
1OpenAIMoins cher
$0.00001
$0.00003
2FrogBot
$2.5
$15
3Neon
$5
$30

Comparer les prix entre différents fournisseurs API pour ce modèle.

Sources externes

LLM StatsArtificial Analysis