Skip to main content

GPT-4o (May '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.

Release Date
2024-05-13
Parameters
Context Length
128K
Modalities
image, pdf, text

Capability Radar

27
general
28
coding
40
reasoning
35
scienceest.
36
agents
85
multimodal

Science uses a reasoning proxy when dedicated science benchmarks are unavailable.

Rankings

Domain#RankScoreSource
Code Ranking273
33.0
AA
General Ranking301
36.0
AA
Math Reasoning204
45.0
AA
Science323
35.0
AA

Benchmark Scores (LLM Stats)

Biology

GPQA53.6%SR

Code

HumanEval90.2%SR

Finance

MMLU88.7%SR
MMLU-Pro72.6%SR

Math

MGSM90.5%SR
DROP83.4%SR
MATH76.6%SR
MathVista63.8%SR

AA Evaluation Indices

Coding Index
24.2
Intelligence Index
8.6
Math 500
0.8
Mmlu Pro
0.7
Gpqa
0.5
Livecodebench
0.3
Scicode
0.3
Aime
0.1
Hle
0.0

LLM Stats Category Scores

Code
90
Language
80
Legal
80
Math
80
Reasoning
80
Finance
80
Healthcare
80
General
70
Multimodal
60
Vision
60
Physics
50
Biology
50
Chemistry
50

Pricing

Input Price$5 / 1M tokens
Output Price$15 / 1M tokens
Blended Price (3:1)$7.5 / 1M tokens
Cache Read Price$1.25 / 1M tokens

Speed

Tokens/sec104.8
Time to First Token0.51s
Time to Answer0.51s

Provider Price Ranking

Provider Price Ranking

2 providers

Cheapest: OpenAIMost Expensive: Azure
ProviderInputOutput
1OpenAICheapest
$0
$0.00001
2Azure
$0
$0.00001

Compare pricing across different API providers for this model.

External Sources