> GPT-5 mini is a closed AI model from OpenAI, released 7 Aug 2025. Index score 143 (GPT-4 = 100), rank 78 of 229 ranked models. API price $0.25 in / $2.0 out per million tokens, 400K context.

[Models](https://themodelindex.org/models/) /[OpenAI](https://themodelindex.org/labs/openai/)

# GPT-5 mini

OpenAI

Released 7 Aug 2025

Closed

[Compare](https://themodelindex.org/compare/gpt-5-mini-vs-qwen3-235b-a22b-thinking-jul-2025/)

143132–155

Index score

#78 of 229 models

6/ 8

Core tests taken

4 of 6 areas · plus 14 anchor tests

−10

Versus the frontier at release

best then: GPT-5

Replaced by [GPT-5.4 Mini](https://themodelindex.org/models/gpt-5-4-mini/)

$0.25/ $2.0

Price per million tokens

input / output, list price

400K

Context window

tokens it reads at once

## Where it sits · on the frontier

_Chart: Model Index score of every scored model since late 2022, with the best closed and best open model over time_

o3 reached this score 4 months earlier.

## Test results · by area · tick = best by any model

Show 11 anchor tests

Reasoning & knowledge

evidence

GPQA Diamond

75%

Humanity's Last Exam

19%

Maths

evidence

FrontierMath T1-3

47%

Coding

evidence

SWE-bench Verified

65%

Terminal-Bench

35%

Agents

evidence

APEX-Agents

no result

Novel problems

evidence

ARC-AGI-2

4%

Long tasks

no evidence yet

METR time horizon

no result

Independent results from the Epoch AI benchmarking hub, best reasoning setting. The core tests are shown here; anchor tests also inform the score and can be shown above.

## What others say · rank on each leaderboard

The Model Index

independent tests, our method

#78

of 219 · 143

Epoch Capabilities Index

overall capability from many benchmarks

#77

of 239 · 145.5

LMArena · Maths

maths questions in chat

#132

of 373 · 1405

LMArena · Text

overall chat quality, judged by people

#155

of 388 · 1390

LMArena · Coding

coding questions in chat

#163

of 383 · 1431

LMArena · Creative writing

creative writing

#185

of 386 · 1324

LMArena · Vision

understanding images

#87

of 149 · 1183

Further left is better. Leaderboards measure different things: LMArena is people voting blind between two answers, the others are test scores. Click any row for the source.

## Best at · top three among current models

3rd

SWE-bench Verified

Epoch AI · independent

Where this model places in the top three of today's models, on category leaderboards and on our core tests.

## Where to use it · prices checked 1 Oct 2026

#### From the lab

ChatGPT

app · subscription

↗

OpenAI API

API

↗

#### API providers · 2 · per million tokens, in / out

O

OpenAI

$0.25 / $2.0

cheapest

A

Azure

$0.28 / $2.2

↗

Provider prices come from OpenRouter's live listing; going direct to a provider can differ. Subscriptions are the lab's own apps.

## Facts and sources

Released

7 Aug 2025

Announcement

not linked yet

Release entry

–

Scored as

GPT-5 mini

Artificial Analysis index

–

Output speed

–

Hugging Face

closed weights

## OpenAI releases · around this one

ChatGPT

Closed

30 NOV 2022

GPT-4

Closed

14 MAR 2023

index 100

---
Source: https://themodelindex.org/models/gpt-5-mini/ · The Model Index · data as of 2026-10-01