llmboard.aiAI model intelligence
Home

Model Rankings

OverallOpen ModelsAgentCodingReasoningMathKnowledgeInstruction FollowingTextVision
Image GenerationImage Editing
Video GenerationImage to VideoVideo Editing
Text to SpeechSpeech to Text
Embeddings

Efficiency

Chat Token PricingImage PricingVideo PricingAudio Pricing
Chat Speed & LatencyProvider Reliability

Benchmarks

GPQAMMLU-ProAIME 2025SWE-Bench VerifiedMMLUHumanity's Last ExamLiveCodeBenchMATHHumanEvalMMMU-Pro
All Benchmarks

Tools

Model DirectoryCompare Models

Scoring & Data

Scoring & Data
393 models668 benchmarks

Leaderboard Center

Overall RankingCodingCore BenchmarksPrice & ValueRuntime Performance

Modalities

All ModelsImage GenerationImage EditingVideo GenerationImage-to-VideoVideo EditingText-to-SpeechSpeech-to-TextEmbeddings

Data & Methods

Scoring MethodAll BenchmarksReasoningMath

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai

OpenAI model product

GPT-5.4-mini

4 mini is OpenAI's strongest mini model yet for coding, computer use, and subagents.

Updated Aug 17, 2026. Default version: GPT-5.4 mini

Compare
LLMBoard Score60.2GPT-5.4 mini
Coverage60%15 benchmark families
Context window400KTokens
Official input price$0.75OpenAI API

On this page

  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Runtime
  • Specification
  • Versions
  • Compare
  • Similar models
  • About
  • FAQ

GPT-5.4-mini Capability Profile

This profile uses the model's current scored version. Arena ratings and prices are shown separately.

GPT-5.4 mini LLMBoard score breakdown

GPT-5.4-mini Benchmark Results

Benchmark scores for GPT-5.4 mini.

15 rows
Columns

Show columns

Sort by
Benchmark
Score
Rank
Participants
Percentile
Evidence
Evaluated
BenchmarkGraphwalks BFS <128kScore76.3%Rank04Participants11Percentile70.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkGraphwalks parents <128kScore71.5%Rank05Participants11Percentile60.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkFinance Agent v2Score45.4%Rank10Participants26Percentile64.0%EvidenceBEvaluatedAug 17, 2026
BenchmarkOmniDocBench 1.5Score87.4%Rank12Participants18Percentile35.3%EvidenceCEvaluatedAug 17, 2026
BenchmarkLegal Agent BenchmarkScore0.0%Rank13Participants13Percentile0.0%EvidenceBEvaluatedAug 17, 2026
BenchmarkMRCR v2 (8-needle)Score33.6%Rank13Participants23Percentile45.5%EvidenceCEvaluatedAug 17, 2026
BenchmarkTau2 TelecomScore93.4%Rank13Participants35Percentile64.7%EvidenceCEvaluatedAug 17, 2026
BenchmarkOSWorld-VerifiedScore72.1%Rank16Participants24Percentile34.8%EvidenceCEvaluatedAug 17, 2026
BenchmarkTerminal-Bench 2.0Score60.0%Rank20Participants51Percentile62.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkMMMU-ProScore76.6%Rank27Participants68Percentile61.2%EvidenceCEvaluatedAug 17, 2026
BenchmarkToolathlonScore42.9%Rank29Participants37Percentile22.2%EvidenceCEvaluatedAug 17, 2026
BenchmarkMCP AtlasScore57.7%Rank30Participants33Percentile9.4%EvidenceCEvaluatedAug 17, 2026
BenchmarkSWE-Bench ProScore54.4%Rank36Participants50Percentile28.6%EvidenceCEvaluatedAug 17, 2026
BenchmarkGPQAScore88.0%Rank39Participants239Percentile84.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkHumanity's Last ExamScore28.2%Rank51Participants99Percentile49.0%EvidenceCEvaluatedAug 17, 2026

GPT-5.4-mini Arena Results

Preference and agent-evaluation results for the default version.

6 rows
Columns

Show columns

Sort by
Arena
Category
Rank
Rating / score
Votes
Observations
Result date
Arenavision style controlCategoryoverallRank37Rating / score1253.2Votes23,433ObservationsN/AResult dateAug 6, 2026
ArenavisionCategoryoverallRank52Rating / score1246.4Votes23,433ObservationsN/AResult dateAug 6, 2026
Arenatext factualityCategoryoverallRank55Rating / score1448.7Votes59,487ObservationsN/AResult dateAug 12, 2026
ArenawebdevCategoryoverallRank65Rating / score1397.0Votes11,290ObservationsN/AResult dateAug 14, 2026
Arenatext style controlCategoryoverallRank66Rating / score1448.2Votes59,631ObservationsN/AResult dateAug 12, 2026
ArenatextCategoryoverallRank116Rating / score1412.1Votes59,631ObservationsN/AResult dateAug 12, 2026

GPT-5.4-mini Pricing

Official vendor API pricing appears first, followed by individual provider offers.

Official API
$0.75 input, $4.5 output per 1M
Official provider
OpenAI
Lowest third-party
From $0.375 input, $4 output per 1M via Xpersona
Tracked offerings
35
30 of 34 rows
Columns

Show columns

Sort by
Provider
Provider model ID
Region
Input / 1M
Output / 1M
Context
Updated
ProviderKenariProvider model IDgpt-5-4-miniRegionglobalInput / 1MN/AOutput / 1MN/AContext400KUpdatedAug 17, 2026
ProviderXpersonaProvider model IDgpt-5.4-miniRegionglobalInput / 1M$0.375Output / 1M$4Context272KUpdatedAug 17, 2026
ProviderPoeProvider model IDopenai/gpt-5.4-miniRegionglobalInput / 1M$0.68Output / 1M$4Context400KUpdatedAug 17, 2026
ProviderOrcaRouterProvider model IDopenai/gpt-5.4-miniRegionglobalInput / 1M$0.75Output / 1M$4.5Context400KUpdatedAug 17, 2026
ProviderNanoGPTProvider model IDopenai/gpt-5.4-miniRegionglobalInput / 1M$0.75Output / 1M$4.5Context400KUpdatedAug 17, 2026
ProviderImpossiblProvider model IDopenai/gpt-5.4-miniRegionglobalInput / 1M$0.75Output / 1M$4.5Context400KUpdatedAug 17, 2026
ProviderOpenRouterProvider model IDopenai/gpt-5.4-miniRegionglobalInput / 1M$0.75Output / 1M$4.5Context400KUpdatedAug 17, 2026
ProviderCrossModelProvider model IDopenai/gpt-5.4-miniRegionglobalInput / 1M$0.75Output / 1M$4.5Context400KUpdatedAug 17, 2026
ProviderDatabricksProvider model IDdatabricks-gpt-5-4-miniRegionglobalInput / 1M$0.75Output / 1M$4.5Context400KUpdatedAug 17, 2026
ProviderOpenAIProvider model IDgpt-5.4-miniRegionglobalInput / 1M$0.75Output / 1M$4.5Context400KUpdatedAug 17, 2026
ProviderVivgridProvider model IDgpt-5.4-miniRegionglobalInput / 1M$0.75Output / 1M$4.5Context400KUpdatedAug 17, 2026
ProviderNEAR AI CloudProvider model IDopenai/gpt-5.4-miniRegionglobalInput / 1M$0.75Output / 1M$4.5Context400KUpdatedAug 17, 2026
ProviderMerge GatewayProvider model IDopenai/gpt-5.4-miniRegionglobalInput / 1M$0.75Output / 1M$4.5Context400KUpdatedAug 17, 2026
ProviderCloudflare AI GatewayProvider model IDopenai/gpt-5.4-miniRegionglobalInput / 1M$0.75Output / 1M$4.5Context400KUpdatedAug 17, 2026
ProviderFastRouterProvider model IDopenai/gpt-5.4-miniRegionglobalInput / 1M$0.75Output / 1M$4.5Context400KUpdatedAug 17, 2026
ProviderZenMuxProvider model IDopenai/gpt-5.4-miniRegionglobalInput / 1M$0.75Output / 1M$4.5Context400KUpdatedAug 17, 2026
ProviderFreeModelProvider model IDgpt-5.4-miniRegionglobalInput / 1M$0.75Output / 1M$4.5Context400KUpdatedAug 17, 2026
ProviderOfoxProvider model IDopenai/gpt-5.4-miniRegionglobalInput / 1M$0.75Output / 1M$4.5Context400KUpdatedAug 17, 2026
ProviderNeonProvider model IDgpt-5-4-miniRegionglobalInput / 1M$0.75Output / 1M$4.5Context400KUpdatedAug 17, 2026
ProviderAzure Cognitive ServicesProvider model IDgpt-5.4-miniRegionglobalInput / 1M$0.75Output / 1M$4.5Context400KUpdatedAug 17, 2026
Provider302.AIProvider model IDgpt-5.4-miniRegionglobalInput / 1M$0.75Output / 1M$4.5Context400KUpdatedAug 17, 2026
ProviderOpenCode ZenProvider model IDgpt-5.4-miniRegionglobalInput / 1M$0.75Output / 1M$4.5Context400KUpdatedAug 17, 2026
ProviderAzureProvider model IDgpt-5.4-miniRegionglobalInput / 1M$0.75Output / 1M$4.5Context400KUpdatedAug 17, 2026
ProviderFrogBotProvider model IDgpt-5-4-miniRegionglobalInput / 1M$0.75Output / 1M$4.5Context400KUpdatedAug 17, 2026
ProviderAIHubMixProvider model IDgpt-5.4-miniRegionglobalInput / 1M$0.75Output / 1M$4.5Context400KUpdatedAug 17, 2026
ProviderVercel AI GatewayProvider model IDopenai/gpt-5.4-miniRegionglobalInput / 1M$0.75Output / 1M$4.5Context400KUpdatedAug 17, 2026
ProviderEden AIProvider model IDopenai/gpt-5.4-miniRegionglobalInput / 1M$0.75Output / 1M$4.5Context400KUpdatedAug 17, 2026
ProviderEden AIProvider model IDopenai/gpt-mini-latestRegionglobalInput / 1M$0.75Output / 1M$4.5Context400KUpdatedAug 17, 2026
ProviderLLM GatewayProvider model IDgpt-5.4-miniRegionglobalInput / 1M$0.75Output / 1M$4.5Context400KUpdatedAug 17, 2026
ProviderGitHub CopilotProvider model IDgpt-5.4-miniRegionglobalInput / 1M$0.75Output / 1M$4.5Context400KUpdatedAug 17, 2026
ProviderKilo GatewayProvider model IDopenai/gpt-5.4-miniRegionglobalInput / 1M$0.75Output / 1M$4.5Context400KUpdatedAug 17, 2026
ProviderPioneerProvider model IDgpt-5.4-miniRegionglobalInput / 1M$0.75Output / 1M$4.5Context400KUpdatedAug 17, 2026
ProviderAbacusProvider model IDgpt-5.4-miniRegionglobalInput / 1M$0.75Output / 1M$4.5Context400KUpdatedAug 17, 2026
ProviderVenice AIProvider model IDopenai-gpt-54-miniRegionglobalInput / 1M$0.9375Output / 1M$5.63Context400KUpdatedAug 17, 2026

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

GPT-5.4-mini Runtime Performance

Provider-specific output speed and catalog latency for GPT-5.4 mini. Runtime does not affect the capability score.

No runtime data

No provider-specific speed or latency record is linked to the default version yet.

Browse runtime rankings

Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.

GPT-5.4-mini Specifications

Technical details for the model's default version.

Version
GPT-5.4 mini
Released
Mar 17, 2026
Knowledge cutoff
Aug 31, 2025
Parameters
N/A
Context window
400K
Max output
128K
Inputs
image, text
Outputs
text
Open weights
No
License
Proprietary

GPT-5.4-mini Versions

Available versions of this model. The score column identifies the version used in the overall ranking.

1 rows
Columns

Show columns

Sort by
Version
Released
LLMBoard
Parameters
Context
Max output
Open weights
License
VersionGPT-5.4 miniReleasedMar 17, 2026LLMBoard60.2ParametersN/AContext400KMax output128KOpen weightsNoLicenseProprietary

GPT-5.4-mini vs nearby models

Open a comparison with the three ranked models immediately above and below this model.

GPT-5.4-minivsKimi K2 ThinkingGPT-5.4-minivsStep 3.5 FlashGPT-5.4-minivsLongCat Flash ThinkingGPT-5.4-minivsQwen3.6 27BGPT-5.4-minivsGemma 4 31BGPT-5.4-minivsGLM 4.7

Models similar to GPT-5.4-mini

Recommendations prioritize the same model type and family, then the closest LLMBoard score.

#60+0.9
OP

GPT-5.1-Instant

OpenAI

61.1 LLMBoard

DetailsCompare
#68-1.0
OP

GPT-5.2-Codex

OpenAI

59.2 LLMBoard

DetailsCompare
#58+2.0
OP

GPT-5.1

OpenAI

62.2 LLMBoard

DetailsCompare
#55+2.8
OP

GPT-5.3-Codex

OpenAI

62.9 LLMBoard

DetailsCompare
#86-6.6
OP

GPT-5.5-Instant

OpenAI

53.5 LLMBoard

DetailsCompare
#90-7.8
OP

o3

OpenAI

52.4 LLMBoard

DetailsCompare

What is GPT-5.4-mini?

Key information about GPT-5.4-mini and its available data.

4 mini is OpenAI's strongest mini model yet for coding, computer use, and subagents. 4 to a faster, more efficient model designed for high-volume workloads, with strong coding, reasoning, multimodal understanding, and tool use.

Data as of 2026-08-17.

FAQ

Common questions about GPT-5.4-mini.

When was GPT-5.4-mini released?

GPT-5.4-mini's default version was released on Mar 17, 2026.

How much does GPT-5.4-mini cost?

GPT-5.4-mini's official API price is $0.75 per million input tokens and $4.5 per million output tokens via OpenAI. The lowest tracked third-party offer starts at $0.375 input and $4 output via Xpersona.

Who created GPT-5.4-mini?

GPT-5.4-mini was created by OpenAI.

What is the context window for GPT-5.4-mini?

The default version has a 400K token context window.

Is GPT-5.4-mini open weight?

No. The default version is not marked as having publicly available weights.

How many API providers offer GPT-5.4-mini?

35 provider offerings are linked to the default version.

What models should I compare GPT-5.4-mini with?

Nearby ranked alternatives include Kimi K2 Thinking, Step 3.5 Flash, LongCat Flash Thinking.