> GPT-5.4 Mini is a closed AI model from OpenAI, released 17 Mar 2026. Index score 151 (GPT-4 = 100), rank 58 of 229 ranked models. API price $0.75 in / $4.5 out per million tokens, 400K context.

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

# GPT-5.4 Mini

OpenAI

Released 17 Mar 2026

Closed

[Compare](https://themodelindex.org/compare/gpt-5-4-mini-vs-glm-5-1/)

151139–162

Index score

#58 of 229 models

3/ 8

Core tests taken

3 of 6 areas · plus 12 anchor tests

−20

Versus the frontier at release

best then: GPT-5.4

$0.75/ $4.5

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_

GPT-5 reached this score 7 months earlier.

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

Show 11 anchor tests

Reasoning & knowledge

evidence

GPQA Diamond

87%

Humanity's Last Exam

no result

Maths

evidence

FrontierMath T1-3

51%

Coding

evidence

SWE-bench Verified

no result

Terminal-Bench

no result

Agents

evidence

APEX-Agents

no result

Novel problems

evidence

ARC-AGI-2

19%

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

#58

of 219 · 151

LMArena · Text

overall chat quality, judged by people

#74

of 388 · 1447

LMArena · Coding

coding questions in chat

#79

of 383 · 1495

LMArena · Maths

maths questions in chat

#83

of 373 · 1439

Epoch Capabilities Index

overall capability from many benchmarks

#56

of 239 · 148.8

LMArena · Creative writing

creative writing

#94

of 386 · 1402

LMArena · Vision

understanding images

#44

of 149 · 1251

LMArena · WebDev

building web apps and front ends

#79

of 123 · 1397

LiveBench · Overall

overall, with fresh questions to limit contamination

#55

of 58 · 66.4

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

Not in the top three among current models on any category we track.

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

$1.5 / $9.0

cheapest

A

Azure

$0.82 / $4.95

↗

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

17 Mar 2026

Announcement

not linked yet

Release entry

–

Scored as

GPT-5.4 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-5-4-mini/ · The Model Index · data as of 2026-10-01