Browse all OpenAI text models
Provider logo

GPT-4o (2024-08-06)

openai/gpt-4o-2024-08-06
Provider logo

GPT-4o (2024-08-06)

openai/gpt-4o-2024-08-06

OpenAI's precusor to ChatGPT-4o. Great on English text and code, with significant improvements on text in non-English languages.

Context Window

128.0K

Max Output

16.4K

Avg output tokens (7d)

48 tokens

2%

Input Price (Auto)

$2.50/1M

Output Price (Auto)

$10.00/1M

Cache Read (Auto)

$1.25/1M

Capabilities

Benchmarks

Performance metrics and benchmarks

Sourced from Artificial Analysis.

Intelligence Index

7.7

Better than 30% of models compared

Agentic work

T²-Bench Telecom (legacy)

Legacy fallback · Conversational AI agents in dual-control scenarios

28.9%

Better than 36% of models compared

Document reasoning

AA-LCR v1.1

Long context reasoning with updated grading

41.0%

Better than 40% of models compared

Reasoning

HLE

Humanity's Last Exam

2.3%

Better than 0% of models compared

IFBench

Instruction-following benchmark

36.0%

Better than 27% of models compared

CritPt

Research-level physics reasoning

0.0%

Coding

Terminal-Bench Hard (legacy)

Legacy fallback · Agentic coding and terminal use

8.3%

Better than 42% of models compared

LiveCodeBench

Contamination-free coding benchmark

31.7%

Better than 38% of models compared

Math

AIME

American Invitational Mathematics Examination

11.7%

Better than 37% of models compared

Math-500

Diverse mathematical problem solving benchmark

79.5%

Better than 45% of models compared

Knowledge

AA-Omniscience Accuracy

Proportion of correctly answered questions

23.7%

AA-Omniscience Hallucination Rate

Rate of incorrect answers among non-correct responses

58.4%

Legacy benchmarks

GPQA Diamond (legacy)

Graduate-level scientific reasoning

52.1%

Better than 26% of models compared

AA-LCR (unversioned / legacy)

Long context reasoning evaluation

41.0%

Better than 40% of models compared

Last updated Sep 13, 2026

Artificial Analysis

Providers

Auto routing is available for this model. Explicit provider selection is not available.

Loading provider options…