VerdictPal
Join

Models / OpenAI

GPT 5.4

GPT 5 · Released 2026-03-05

OpenAI's March 2026 model.

Default for production OpenAI workloads where GPT 5.5 is overkill but GPT 5.2 is too old.

Composite63
Context256K
Input / 1M$7.0
Output / 1M$28
Knowledge cutoff2026-01-31
Output speed94 t/s
Statusflagship
ChatGPTCursorPerplexityScira AI

Family profile

Best published score in each covered benchmark family.

69/100 avg
Reasoning
92
Math
48
Coding
52
Long context
82

4 tested benchmark families

Editor's note
GPT 5.4 is the OpenAI model we recommend when GPT 5.5 is too expensive but the task still needs frontier coding. The ForgeCode variant of Terminal-Bench 2.0 (81.8%) is the most reproducible number we have on the model.
Benchmark placements

Where GPT 5.4 places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.

BenchmarkFamilyRankScoreSourceDate
FrontierMathMath#4/ 1548Epoch AI FrontierMath Tiers 1-3 (v2) CSV2026-08-15
DeepSWECoding#6/ 852DeepSWE leaderboard v1.12026-06-20
Humanity's Last ExamReasoning#22/ 18644Artificial Analysis2026-09-28
AA-LCRLong context#23/ 18482Artificial Analysis2026-09-28
GPQA DiamondReasoning#27/ 18492Artificial Analysis2026-09-28
AA output speedPerformance#64/ 195Artificial Analysis2026-10-12
Family context

The three highest-scoring models with pages in each capability family. Where GPT 5.4 shows up, it's highlighted.

MathGPT 5.4 · 48
  1. 1
    GPT 5.5
    52
  2. 2
    GPT-5.5 Pro
    52
  3. 3
    GPT-5.4 Pro
    50
Long contextGPT 5.4 · 82
  1. 1
    Kimi K3
    89
  2. 2
    MiMo-V2.6-Pro
    86
  3. 3
    Claude Fable 5.1
    85
Newest receipts

Benchmark rows added to the public ledger for GPT 5.4 in the last 120 days. Older rows live in the full table below.

5 recent
BenchmarkFamilyScoreSourceDays ago
AA output speedPerformance94 t/sArtificial Analysis10
AA-LCRLong context82%Artificial Analysis24
GPQA DiamondReasoning92%Artificial Analysis24
Humanity's Last ExamReasoning43.7%Artificial Analysis24
FrontierMathMath47.6%Epoch AI FrontierMath Tiers 1-3 (v2) CSV68
Family coverage

A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.

Reasoning92
Math48
Coding52
Long context82
Price vs. performance
0255075100$0.10$0.30$1$3$10$30input USD / 1M tokens · log scale →← intelligence

Hover any dot for name, score, and input price. Keyboard: tab through the top twelve, or use the ranking below.

AnthropicOpenAIGoogleAlibabaMetaZhipuxAIDeepSeekMiniMaxXiaomiMoonshotOtherMeituanMistralNVIDIACohere

Full benchmark ledger

Every catalog benchmark for GPT 5.4. Scores link to the original source; gaps mean no public row exists yet.

6 sourced rows

6 of 13 catalog benchmarks have a sourced row for GPT 5.4.

Reasoning

Math

Coding

Long context

Performance

Changelog
  1. GPT 5.2 retired for general availability.
Sources

Questions this model page answers

Every answer below is assembled from the dated fields on this page. Nothing is written separately for search.

What is GPT 5.4?

GPT 5.4 is a OpenAI model: OpenAI's March 2026 model.

What is GPT 5.4 for?

Default for production OpenAI workloads where GPT 5.5 is overkill but GPT 5.2 is too old.

What does GPT 5.4 cost?

GPT 5.4 lists $7.0 input and $28 output per 1M tokens. Pricing last checked 2026-06-01.

How large is the GPT 5.4 context window?

GPT 5.4 publishes a 256K token context window.

What is the VerdictPal status of GPT 5.4?

GPT 5.4 carries Flagship status on the model atlas.

The Pack · Editorial newsletter

Know when the rules move.

One short email when a university changes its AI rule for theses, or a research tool changes its pricing or privacy terms. No tracking, no third-party analytics. Unsubscribe in one click.

The thesis AI checklist is free to use, no signup needed →