GENAIWIKI

OpenAI

GPT-4o

Multimodal LLM · Release May 13, 2024 · Proprietary API

Flagship multimodal model tuned for tool use, vision understanding, and low-latency chat experiences across consumer and enterprise surfaces.

frontiergeneral-purposemultimodal
Updated today

Modalities

What goes in and what comes out.

Inputs

text, image, audio

Outputs

text

Capabilities

tool use, vision, json mode, function calling

Benchmarks snapshot

Structured JSON for reproducible comparisons.

{
  "mmlu": 88.7,
  "humaneval": 90.2
}

Related on GenAIWiki

Same provider, tooling that cites the model, or prompts tuned for it.