GPT-4o (Aug '24)
OpenAIGPTProprietary
Description
GPT-4o ('o' for 'omni') is a multimodal AI model that accepts text, audio, image, and video inputs, and generates text, audio, and image outputs. It matches GPT-4 Turbo performance on text and code, with improvements in non-English languages, vision, and audio understanding.
Date de sortie
2024-08-06
Paramètres
—
Longueur du contexte
128K
Modalités
file, image, text
Radar de capacités
15
general
24
coding
40
reasoning
36
scienceest.
50
agents
90
multimodal
Science utilise un proxy de raisonnement lorsque les benchmarks scientifiques dédiés ne sont pas disponibles.
Classements
| Domaine | #Rang | Score | Source |
|---|---|---|---|
| Code Ranking | 265 | 30.0 | AA |
| General Ranking | 377 | 28.0 | AA |
| Math Reasoning | 196 | 46.0 | AA |
| Multimodal Ranking | 27 | 81.0 | LS |
| Reasoning | 94 | 37.0 | LS |
| Science | 290 | 37.0 | AA |
Scores de benchmarks (LLM Stats)
Biology
GPQA
70.1%Aut.
Code
SWE-Bench Verified
33.2%Aut.
SWE-Lancer
32.6%Aut.
Aider-Polyglot
30.7%Aut.
Aider-Polyglot Edit
18.2%Aut.
SWE-Lancer (IC-Diamond subset)
12.4%Aut.
Communication
Tau2 Retail
63.4%Aut.
Multi-IF
60.9%Aut.
TAU-bench Retail
60.3%Aut.
Tau2 Airline
45.5%Aut.
TAU-bench Airline
42.8%Aut.
Multi-Challenge
40.3%Aut.
Tau2 Telecom
23.5%Aut.
Factuality
SimpleQA
38.2%Aut.
Finance
MMLU
85.7%Aut.
MMLU-Pro
74.7%Aut.
General
MMMLU
81.4%Aut.
IFEval
81.0%Aut.
MMMU
72.2%Aut.
MMMU-Pro
59.9%Aut.
Internal API instruction following (hard)
29.2%Aut.
Healthcare
VideoMMMU
61.2%Aut.
Image To Text
DocVQA
92.8%Aut.
Language
COLLIE
61.0%Aut.
Long Context
EgoSchema
72.2%Aut.
ComplexFuncBench
66.5%Aut.
OpenAI-MRCR: 2 needle 128k
31.9%Aut.
Math
MathVista
61.4%Aut.
AIME 2024
13.1%Aut.
Humanity's Last Exam
5.3%Aut.
Multimodal
AI2D
94.2%Aut.
ChartQA
85.7%Aut.
CharXiv-D
85.3%Aut.
CharXiv-R
58.8%Aut.
Reasoning
Graphwalks BFS <128k
41.7%Aut.
Graphwalks parents <128k
35.4%Aut.
ERQA
35.2%Aut.
Video
ActivityNet
61.9%Aut.
Indices d'évaluation AA
Intelligence Index18.6
Coding Index16.6
Math 5000.8
Gpqa0.5
Ifbench0.4
Lcr0.3
Scicode0.3
Livecodebench0.3
Tau20.3
Aime0.1
Terminalbench Hard0.1
Hle0.0
Scores par catégorie LLM Stats
Image To Text90
Finance80
Legal80
Vision70
Biology70
Chemistry70
Healthcare70
Instruction Following70
Language70
Multimodal70
Physics70
Structured Output60
Writing60
General60
Long Context60
Tool Calling50
Communication50
Math50
Reasoning50
Spatial Reasoning40
Factuality40
Code30
Frontend Development30
Tarification
Prix d'entrée$2.5 / 1M tokens
Prix de sortie$10 / 1M tokens
Prix mixte (3:1)$4.375 / 1M tokens
Vitesse
Tokens/sec102.1 tokens/s
Délai du premier token0.65s
Temps de réponse0.65s
Fournisseurs disponibles
(Unités internes LS)| Fournisseur | Prix d'entrée | Prix de sortie |
|---|---|---|
| OpenAI | 2.5M | 10.0M |
| Azure | 2.5M | 10.0M |