GPT-4o mini

Name: GPT-4o mini
Author: OpenAI

Foundation modelGPT MiniGPT-4o

GPT-4o mini

Release date: 2024-07-18Updated: 2024-07-19Views: 1,150

Live demoGitHubHugging FaceCompare

Parameters

No data

Context length

128K

Multilingual

Supported

Reasoning ability

No data

GPT-4o mini is an AI model published by OpenAI, released on 2024-07-18, for Foundation model, and 128K context length, with a 871.00 score on Creative Writing.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

GPT-4o mini

Model basics

Reasoning traces

No data

Thinking modes

Thinking modes not supported

Context length

128K tokens

Max output length

No data

Model type

Foundation model

Modality (in / out)

No data

Release date

2024-07-18

Model file size

No data

MoE architecture

Total params / Active params

No data / Not applicable

Knowledge cutoff

No data

GPT-4o mini

Open source & experience

Code license

Proprietary

Weights license

Proprietary

GitHub repo

N/A

Hugging Face

N/A

Live demo

N/A

GPT-4o mini

Official resources

Paper

DataLearnerAI blog

N/A

GPT-4o mini

API details

API speed

No data

No public API pricing yet.

GPT-4o mini

Benchmark Results

GPT-4o mini currently shows benchmark results led by MBPP (6 / 96, score 87.20), GSM8K (14 / 70, score 91.30), HumanEval (33 / 140, score 87.20). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

General Knowledge

3 evaluations

Benchmark / mode

Score

Rank/total

MMLU

Standard Mode

48 / 124

MMLU Pro

Standard Mode

61.70

110 / 134

GPQA

Standard Mode

40.20

14 / 17

Math and Reasoning

2 evaluations

Benchmark / mode

Score

Rank/total

GSM8K

Standard Mode

91.30

14 / 70

MATH

Standard Mode

70.20

19 / 42

Coding and Software Engineer

3 evaluations

Benchmark / mode

Score

Rank/total

HumanEval

Standard Mode

87.20

33 / 140

MBPP

Standard Mode

87.20

6 / 96

WeirdML v2

Standard ModeTools

11.76

51 / 52

General Evaluation

1 evaluations

Benchmark / mode

Score

Rank/total

GPQA Diamond

Standard Mode

41.10

258 / 274

Common Sense

1 evaluations

Benchmark / mode

Score

Rank/total

SimpleQA

Standard Mode

9.50

43 / 47

Writing and Creative Capabilities

1 evaluations

Benchmark / mode

Score

Rank/total

Creative Writing

Standard Mode

871

92 / 106

Common Sense Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

SimpleBench

Standard Mode

10.70

92 / 92

Agent Level Benchmark

2 evaluations

Benchmark / mode

Score

Rank/total

BALROG

Standard ModeTools

17.40

12 / 12

Aider-Polyglot

Standard Mode

3.60

59 / 59

Claw-style Agent Evaluation

1 evaluations

Benchmark / mode

Score

Rank/total

Pinch Bench

Thinking ModeTools

28 / 38

Multimodal Understanding

2 evaluations

Benchmark / mode

Score

Rank/total

GeoBench ACW

Standard Mode

15 / 20

VPCT

Standard Mode

23 / 24

View benchmark analysis Compare with other models

GPT-4o mini

Publisher

OpenAI

View publisher details

GPT-4o mini

Model Overview

GPT-4o mini is an AI model published by OpenAI, released on 2024-07-18, for Foundation model, and 128K context length, with a 871.00 score on Creative Writing.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.