BenchLeader
Menu
Best LLMsChoose a modelLeaderboardsModelsBenchmarksProvidersReleases9

GPT-5.4 vs GPT-5.4 Pro

Full profiles: GPT-5.4 (OpenAI) and GPT-5.4 Pro (OpenAI): every benchmark, price and rank.

Updated · Data from 10 sources

As of 25 Oct 2026, GPT-5.4 (xhigh) and GPT-5.4 Pro are neck and neck on quality (64.7 vs 63.3 on the BenchLeader Index, inside the ±4.3 margin of error), and GPT-5.4 (xhigh) costs 12× less, which makes it the better buy for most workloads. Pick GPT-5.4 for instruction following (72 vs 64); pick GPT-5.4 Pro for knowledge (74 vs 60).

GPT-5.4 benchmarks xhigh OpenAI GPT-5.4 Pro benchmarks OpenAIOpen in the comparison tool

Which to pick for…

The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.

Use casePickWhyConfidence
ReasoningGPT-5.4 Pro73 vs 69 category score; Humanity's Last Exam 44.3% vs 36.2%Medium
KnowledgeGPT-5.4 Pro74 vs 60 category scoreHigh
Images and other mediaGPT-5.4 Pro70 vs 61 category scoreHigh
Following instructionsGPT-5.472 vs 64 category scoreHigh
Lowest costGPT-5.4$5.63 vs $67.50 per 1M blended; agentic coding session $0.210 vs $2.52–
Fastest first answerGPT-5.4 Pro6.1 s (GPT-5.4 Pro) vs 118.0 s (GPT-5.4 (xhigh)) to the first answer token–
High volume on a budgetNeither flagshipA smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs–

Key differences

  • GPT-5.4 (xhigh) and GPT-5.4 Pro are neck and neck on quality (64.7 vs 63.3, within the ±4.3 margin).
  • GPT-5.4 (xhigh) is stronger in agents & tools, coding, composite, instruction following, long context, maths.
  • GPT-5.4 Pro is stronger in knowledge, multimodal, reasoning.
  • GPT-5.4 (xhigh) is 12× cheaper ($5.63 vs $67.50 per 1M blended).
  • GPT-5.4 (xhigh) streams 13.8× faster (96 vs 7 tokens per second).

At a glance

SpecGPT-5.4GPT-5.4 Pro
DeveloperOpenAIOpenAI
Released5 Mar 20264 Mar 2026
Context window (tokens)1,050,0001,050,000
Compared atGPT-5.4 (xhigh)GPT-5.4 Pro
Open weightsNoNo
Price in / out / cached input per 1M$2.50 / $15.00 / $0.250$30.00 / $180.00 / –

Category by category

Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.

CategoryGPT-5.4 (xhigh)GPT-5.4 ProLeader
Reasoning69.172.5GPT-5.4 Pro
Coding64.6–not comparable
Agents & tools63.6–not comparable
Maths65.2–not comparable
Knowledge59.773.6GPT-5.4 Pro
Instruction following72.363.8GPT-5.4
Multimodal61.469.8GPT-5.4 Pro
Long context66.1–not comparable
Composite73.1–not comparable

Where sources disagree

Across the 1 benchmarks both have, GPT-5.4 leads 0, GPT-5.4 Pro leads 1.

Overall indexGPT-5.4 (xhigh)GPT-5.4 ProLeader
BenchLeader Index64.763.3neck and neck

Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).

Price, speed and latency

List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page; suite cost is what Artificial Analysis paid to run its whole Intelligence Index.

MeasureGPT-5.4 (xhigh)GPT-5.4 Pro
Blended price per 1M tokens$5.63$67.50
Input / output per 1M$2.50 / $15.00$30.00 / $180.00
Cached input per 1M$0.250–
Price per task: chat reply$0.0055$0.066
Price per task: summarize a 30-page report$0.039$0.468
Price per task: code edit$0.037$0.450
Price per task: agentic coding session$0.210$2.52
Price per task: structured extraction$0.0080$0.096
Output speed96 tok/s7 tok/s
Time to first answer118.0 s6.1 s
Time to a complete answer123.2 s–

Each model is compared at its best-ranked reasoning-effort setting. GPT-5.4 (xhigh) scores 64.7 and takes 118 s to its first answer token; GPT-5.4 (low) scores 59.7 in 2 s, GPT-5.4 (high) scores 58.9 in 1 s. GPT-5.4 Pro scores 63.3 and takes 6 s to its first answer token; GPT-5.4 Pro (xhigh) scores 61.9 in 6 s. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.

Every benchmark

116 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.

MetricPublisherGPT-5.4 (xhigh)GPT-5.4 Pro
BenchLeader IndexBenchLeader64.763.3
Agents & tools scoreBenchLeader63.6–
Coding scoreBenchLeader64.6–
Composite scoreBenchLeader73.1–
Instruction following scoreBenchLeader72.363.8
Knowledge scoreBenchLeader59.773.6
Long context scoreBenchLeader66.1–
Maths scoreBenchLeader65.2–
Multimodal scoreBenchLeader61.469.8
Reasoning scoreBenchLeader69.172.5
Blended price $/MBenchLeader$5.63$67.50
Output speedBenchLeader96 tok/s7 tok/s
Time to first answerBenchLeader118.0 s6.1 s
Context windowBenchLeader1,050,000 tokens1,050,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub93.3%94.6%†
Humanity's Last ExamScale AI / CAIS36.2%44.3%
SimpleBenchSimpleBench–74.1%
Arena Hard PromptsArena (LMArena)1487†–
LiveBench 1.0 ReasoningLiveBench88.1%–
GPQA Diamond (AA)Artificial Analysis92.0%–
Humanity's Last Exam (AA)Artificial Analysis43.7%–
GPQA Diamond (Vals)Vals AI91.7%–
Kagi LLM BenchmarkKagi LLM Benchmark63.8%†–
ARC-AGI-1ARC Prize93.7%94.5%†
ARC-AGI-2ARC Prize74.0%83.3%†
ARC-AGI-3ARC Prize0.2%†–
CritPtArtificial Analysis23.4%30.0%†
Chess PuzzlesEpoch AI Benchmarking Hub48.0%59.0%†
Mystery Game PuzzlesEpoch AI Benchmarking Hub37.0%–
CL-benchEpoch AI Benchmarking Hub27.9%–
CL-bench LifeEpoch AI Benchmarking Hub21.7%–
LMCAEpoch AI Benchmarking Hub52.0%–
DTBenchEpoch AI Benchmarking Hub94.4%–
ForecastBenchForecastBench63.1%†–
Coding
SWE-bench Verified (Epoch)Epoch AI Benchmarking Hub76.9%†–
SciCodeSciCode56.6%–
WeirdMLWeirdML77.7%57.4%†
GSO-BenchGSO-Bench31.4%–
Arena CodingArena (LMArena)1511†–
Show all 116 benchmarks
MetricPublisherGPT-5.4 (xhigh)GPT-5.4 Pro
Coding
Arena WebDevArena (LMArena)1401†–
LiveBench 1.0 CodingLiveBench77.5%–
LiveCodeBenchVals AI84.1%–
SWE-bench (Vals)Vals AI78.2%–
SWE-Bench ProScale AI SEAL59.1%–
Code MigrationVals AI35.0%–
ProgramBenchVals AI0.0%–
Vibe Code Bench v1.1Vals AI67.4%–
SWE-Bench Pro (private)Scale AI SEAL59.1%–
SWE Atlas: Codebase QnAScale AI SEAL40.8%–
SWE Atlas: RefactoringScale AI SEAL44.3%–
SWE Atlas: Test WritingScale AI SEAL44.4%–
MirrorCodeEpoch AI Benchmarking Hub15.6%†–
DeepSWE v1.1Epoch AI Benchmarking Hub51.8%–
ALE-BenchEpoch AI Benchmarking Hub1607†–
AlgoTuneAlgoTune1.9†–
Terminal-Bench 2.1 (AA)Artificial Analysis78.3%–
Agents & tools
Terminal-BenchTerminal-Bench81.8%†–
APEX-AgentsMercor52.4%†–
LiveBench Agentic CodingLiveBench53.8%–
Terminal-Bench HardArtificial Analysis57.6%–
τ²-Bench Telecom (AA)Artificial Analysis87.1%–
MCP AtlasScale AI SEAL70.6%–
HiL-BenchScale AI SEAL9.7%†–
τ³-bench Bankingτ²-bench39.4%–
τ³-Banking (AA)Artificial Analysis39.6%–
APEX-Agents (AA)Artificial Analysis33.3%–
Harvey's Legal Agent Benchmark v1Vals AI0.0%–
SkillsBenchVals AI51.7%–
Terminal-Bench 2.0 (Vals)Vals AI58.4%†–
DeepResearch BenchDeepResearch Bench35.1%†–
PostTrainBenchEpoch AI Benchmarking Hub19.0%†–
METR Time HorizonsMETR74.3%–
GBAEvalEpoch AI Benchmarking Hub45.1%†–
Vending-Bench 2Andon Labs6144.2†–
DeepSearchQAGoogle63.7%†–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub78.6%82.5%†
FrontierMath Tier 4Epoch AI Benchmarking Hub49.0%58.5%†
OTIS Mock AIMEEpoch AI Benchmarking Hub95.3%–
ProofBenchVals AI56.0%–
LiveBench MathematicsLiveBench94.2%–
AIME (Vals)Vals AI96.7%–
AIME 2026MathArena99.2%–
HMMT February 2026MathArena97.7%–
USAMO 2026MathArena95.2%–
MathArena ApexMathArena54.2%69.8%†
Arena MathsArena (LMArena)1460†–
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub45.1%46.3%†
LiveBench 1.0 Data AnalysisLiveBench79.3%–
AA-OmniscienceArtificial Analysis5.8–
MMLU-ProVals AI87.5%–
LegalBenchVals AI86.0%–
CorpFinVals AI65.3%–
TaxEvalVals AI74.0%–
MedQAVals AI96.1%–
PRBench FinanceScale AI SEAL45.6%†–
PRBench LegalScale AI SEAL44.4%†–
MultiNRCScale AI SEAL58.3%†62.3%
CaseLaw v2Vals AI63.8%–
MedCodeVals AI41.3%–
MedScribeVals AI77.5%–
EBR-benchEpoch AI Benchmarking Hub25.4%–
AA-Omniscience: accuracyArtificial Analysis50.9%–
AA-Omniscience: non-hallucinationArtificial Analysis8.3%–
Instruction following
LiveBench LanguageLiveBench82.6%–
LiveBench Instruction FollowingLiveBench70.2%–
IFBenchArtificial Analysis74.0%–
MultiChallengeScale AI SEAL–69.2%
TutorBenchScale AI SEAL–56.6%
Arena Instruction FollowingArena (LMArena)1460†–
Human preference
Arena TextArena (LMArena)1465†–
EQ-Bench 4EQ-Bench1260†–
Arena Creative WritingArena (LMArena)1435†–
Arena Multi-turnArena (LMArena)1480†–
Arena Longer QueriesArena (LMArena)1477†–
Multimodal
Arena VisionArena (LMArena)1292†–
MMMU-ProArtificial Analysis78.4%–
VISTAScale AI SEAL50.9%†53.9%
MMMU-Pro (Vals)Vals AI87.5%–
MortgageTaxVals AI68.3%–
SAGEVals AI43.3%–
VTBScale AI SEAL29.2%†–
Blueprint-Bench 2Epoch AI Benchmarking Hub27.1%†–
Long context
AA-LCRArtificial Analysis82.0%–
Arena DocumentArena (LMArena)1470†–
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub157.3†159.6
LiveBench 1.0LiveBench78.0%–
AA Intelligence Index v4.3.2Artificial Analysis39.0–
Vals RSI IndexVals AI15.5%–
Safety & honesty
FORTRESSScale AI SEAL–14.8%
MASKScale AI SEAL89.7%†91.7%

Data as of 2026-10-25. Best configuration of each model; every score links to its source on the model pages.

What changed

  • GPT-5.4 (xhigh): 2 new results (Harvey's Legal Agent Benchmark v1, Vals RSI Index).
  • GPT-5.4 Pro: 1 score revision.
  • GPT-5.4 (xhigh): 2 new results (USAMO 2026, τ³-bench Banking).
  • GPT-5.4 (xhigh): 1 score revision.
  • GPT-5.4 (xhigh): 1 new result (SWE Atlas: Codebase QnA).
  • GPT-5.4 Pro: BenchLeader Index 62.1 → 63.6.
  • GPT-5.4 Pro: 1 new result (MultiNRC).
  • GPT-5.4 Pro: BenchLeader Index 64.0 → 62.1.
  • GPT-5.4 Pro: BenchLeader Index 63.4 → 64.0.
  • GPT-5.4 (xhigh): 1 score revision.

Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs

GPT-5.4 vs GPT-5.4 Pro: questions

Is GPT-5.4 better than GPT-5.4 Pro?
GPT-5.4 (xhigh) and GPT-5.4 Pro are neck and neck on quality (64.7 vs 63.3, within the ±4.3 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 2026-10-25, so check the category scores for your use.
Which is cheaper, GPT-5.4 or GPT-5.4 Pro, and will that change?
GPT-5.4 is cheaper today: $5.63 against $67.50 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Which is better for long documents?
Both accept 1,050,000 tokens of context.
Which has lower latency?
GPT-5.4 Pro answers first: 6.1 s against 118.0 s to the first answer token, as Artificial Analysis measures it. Reasoning effort drives most of this: a higher setting thinks longer before it answers.
Which is faster, GPT-5.4 or GPT-5.4 Pro?
GPT-5.4 streams faster: 96 against 7 output tokens per second.
Do independent benchmarks agree on GPT-5.4 vs GPT-5.4 Pro?
Across the 1 benchmarks both have, GPT-5.4 leads 0, GPT-5.4 Pro leads 1.
When was GPT-5.4 released?
GPT-5.4 was released on 5 Mar 2026.