GPT-5 (high)
OpenAIGPTProprietary
Description
GPT-5 is a flagship model from OpenAI designed for coding, reasoning, and agentic tasks across domains. It is optimized for coding and agentic tasks with higher reasoning capabilities and medium speed.
Date de sortie
2025-08-07
Paramètres
—
Longueur du contexte
400K
Modalités
file, image, text
Radar de capacités
55
general
54
coding
95
reasoning
59
scienceest.
80
agents
90
multimodal
Science utilise un proxy de raisonnement lorsque les benchmarks scientifiques dédiés ne sont pas disponibles.
Classements
| Domaine | #Rang | Score | Source |
|---|---|---|---|
| Agents & Tools | 57 | 55.0 | LS |
| Code Ranking | 47 | 74.0 | AA |
| General Ranking | 34 | 83.0 | AA |
| Math Reasoning | 6 | 97.0 | AA |
| Multimodal Ranking | 21 | 84.0 | LS |
| Reasoning | 41 | 72.0 | LS |
| Science | 41 | 74.0 | AA |
Scores de benchmarks (LLM Stats)
Agents
BrowseComp
54.9%Aut.
Biology
GPQA
85.7%Aut.
Code
SWE-Lancer (IC-Diamond subset)
100.0%Aut.
HumanEval
93.4%Aut.
Aider-Polyglot
88.0%Aut.
SWE-Bench Verified
74.9%Aut.
Communication
Tau2 Telecom
96.7%Aut.
Tau2 Retail
81.1%Aut.
Multi-Challenge
69.6%Aut.
Tau2 Airline
62.6%Aut.
Finance
MMLU
92.5%Aut.
General
MMMU
84.2%Aut.
MMMU-Pro
78.4%Aut.
Internal API instruction following (hard)
64.0%Aut.
LongFact Objects
0.8%Aut.
LongFact Concepts
0.7%Aut.
Healthcare
VideoMMMU
84.6%Aut.
HealthBench Hard
1.6%Aut.
Language
COLLIE
99.0%Aut.
Long Context
OpenAI-MRCR: 2 needle 128k
95.2%Aut.
OpenAI-MRCR: 2 needle 256k
86.8%Aut.
Math
AIME 2025
94.6%Aut.
HMMT 2025
93.3%Aut.
MATH
84.7%Aut.
FrontierMath
26.3%Aut.
Humanity's Last Exam
24.8%Aut.
Multimodal
VideoMME w sub.
86.7%Aut.
CharXiv-R
81.1%Aut.
Reasoning
BrowseComp Long Context 128k
90.0%Aut.
BrowseComp Long Context 256k
88.8%Aut.
Graphwalks BFS <128k
78.3%Aut.
Graphwalks parents <128k
73.3%Aut.
ERQA
65.7%Aut.
FActScore
1.0%Aut.
Indices d'évaluation AA
Math Index94.3
Intelligence Index44.6
Coding Index36.0
Math 5001.0
Aime1.0
Aime 250.9
Mmlu Pro0.9
Gpqa0.9
Tau20.8
Livecodebench0.8
Lcr0.8
Ifbench0.7
Scicode0.4
Terminalbench Hard0.3
Hle0.3
Scores par catégorie LLM Stats
Robotics20
Spatial Reasoning6
Multimodal4
Vision3
Reasoning2
Writing100
Language100
Long Context100
Video90
Biology90
Chemistry90
Code90
Finance90
Legal90
Physics90
Tool Calling80
Communication80
General80
Frontend Development70
Healthcare70
Math70
Search70
Structured Output60
Agents50
Tarification
Prix d'entrée$1.25 / 1M tokens
Prix de sortie$10 / 1M tokens
Prix mixte (3:1)$3.438 / 1M tokens
Vitesse
Tokens/sec95.3 tokens/s
Délai du premier token98.86s
Temps de réponse98.86s
Fournisseurs disponibles
(Unités internes LS)Aucune donnée de fournisseur disponible