#33
GPT 4o
gpt-4o

GPT-4o is OpenAI's flagship multimodal model released in May 2024, combining strong general reasoning with native support for text, images, audio, and lightweight video. It matches or exceeds prior GPT-4-class models on benchmarks like MMLU while running roughly twice as fast and at lower cost, making it a practical default for many production workloads. GPT-4o is particularly strong at following complex instructions, maintaining coherent and emotionally-aware dialogue over long contexts, and delivering solid creative writing without sacrificing reliability.

Performance Metrics

Helpfulness
Instruction Following
Comprehension
Empathy
Creative Writing
78.10
Helpfulness
77.74
Empathy
82.55
Instruction Following
85.2
Creative Writing
67.62
Comprehension
77.4
Speed
Avg 82.15 tok/s

Model Specifications

Release Date
May 13, 2024
Lab
OpenAI
Type
Proprietary
Context Size
128K
Max Output Tokens
8.2K
Cost per 1M tokens
$2.50 / $10.00
Model Inputs
Text, Images, Audio, Video
Model Outputs
Text, Audio
Tool Calling
Enabled

Compare With Similar Models