Responsible AI Use Disclaimer: The tools listed are for informational purposes. Users are responsible for adhering to ethical guidelines. Learn more.

OpenAI ProprietaryMay 2024

GPT-4o

OpenAI’s vision-and-voice flagship from 2024 — still a great default.

Intelligence index
72/ 100
vs all models64th pctile
Composite of MMLU, GPQA, MATH & HumanEval
Speed
110tok/s
vs all models59th pctile
Median across providers, steady state
Blended price
$4.38/ 1M tokens
vs all models32th pctile
3:1 input:output blend

At a glance

Context window
128k tokens
Max output
16k tokens
Input price
$2.50 / 1M tokens
Output price
$10.00 / 1M tokens
Time to first token
0.4s
Input modalities
text, image, audio
Output modalities
text, audio
License
Proprietary
Provider
OpenAI

Benchmark scores

Public scores from each provider; bars compare this model against the leader in each benchmark.

MMLU
General knowledge across 57 subjects
88.7
leader: 91.8
MMLU Pro
Harder MMLU successor with more reasoning
73.3
leader: 80.0
GPQA
Graduate-level science Q&A
53.1
leader: 78.0
MATH
Competition mathematics
76.6
leader: 94.8
HumanEval
Python code generation pass@1
90.2
leader: 95.8
Strengths
  • Strong multimodal
  • Voice-native
  • Mature ecosystem
Weaknesses
  • Weaker than GPT-5.5 on reasoning
  • Smaller context vs newer models
Best for
  • General-purpose chat
  • Voice apps
  • Vision tasks

GPT-4o vs… popular head-to-heads

One-click matchups against the models people compare GPT-4o with most.

GPT-4o — frequently asked questions

GPT-4o is a large language model from OpenAI, released on 13 May 2024. OpenAI’s vision-and-voice flagship from 2024 — still a great default.

Need help choosing between models?

Compare every option in one sortable table — intelligence, speed and price on a single page.