BenchLeader

GPT-5.5 vs GPT-5 Pro

Full profiles: GPT-5.5 (OpenAI) and GPT-5 Pro (OpenAI): every benchmark, price and rank.

Updated · Data from 14 sources

As of 16 Nov 2026, GPT-5.5 and GPT-5 Pro are neck and neck on quality (64.1 vs 59.6 on the BenchLeader Index, inside the ±7.5 margin), and GPT-5.5 is 3.7× cheaper at $11.25 vs $41.25 per 1M tokens blended. Choose GPT-5.5 for reasoning (68 vs 55); choose GPT-5 Pro for multimodal (67 vs 62) and knowledge (66 vs 64).

Key facts (as of 16 Nov 2026)

  • GPT-5.5 scores 64.1 on the BenchLeader Index and GPT-5 Pro scores 59.6 (BenchLeader, 16 Nov 2026).
  • GPT-5.5 costs $11.25 per 1M tokens blended (list price, 16 Nov 2026).
  • GPT-5 Pro costs $41.25 per 1M tokens blended (list price, 16 Nov 2026).
  • Of the 3 benchmarks both models have, GPT-5.5 leads 2 (BenchLeader, 16 Nov 2026).

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-5.568 vs 55 category score; ARC-AGI-2 85.0% vs 18.3%High
KnowledgeGPT-5 Pro66 vs 64 category scoreMedium
Images and other mediaGPT-5 Pro67 vs 62 category scoreMedium
Lowest costGPT-5.5$11.25 vs $41.25 per 1M blended; agentic coding session $0.420 vs $1.38–
High volume on a budgetNeither flagshipA smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs–

Key differences

  • GPT-5.5 (xhigh) and GPT-5 Pro are neck and neck on quality (64.1 vs 59.6, within the ±7.5 margin).
  • GPT-5.5 (xhigh) is stronger in reasoning.
  • GPT-5 Pro is stronger in knowledge, multimodal.
  • GPT-5.5 (xhigh) is 3.7× cheaper ($11.25 vs $41.25 per 1M blended).

At a glance

SpecGPT-5.5GPT-5 Pro
DeveloperOpenAIOpenAI
Released23 Apr 20267 Aug 2025
Context window (tokens)1,050,000400,000
Compared atGPT-5.5 (xhigh)GPT-5 Pro
Open weightsNoNo
Price in / out / cached input per 1M$5.00 / $30.00 / $0.500$15.00 / $120.00 / –

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-5.5 (xhigh)GPT-5 ProLeader
Reasoning68.155.0GPT-5.5
Coding60.7–not comparable
Agents & tools61.8–not comparable
Maths69.3–not comparable
Knowledge63.666.1GPT-5 Pro
Instruction following74.0–not comparable
Multimodal62.367.4GPT-5 Pro
Long context66.9–not comparable

On one chart

Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.

2550 avg75ReasoningKnowledgeMultimodalGPT-5.5, Reasoning: 68.1GPT-5.5, Knowledge: 63.6GPT-5.5, Multimodal: 62.3GPT-5 Pro, Reasoning: 55.0GPT-5 Pro, Knowledge: 66.1GPT-5 Pro, Multimodal: 67.4

Not drawn, measured for fewer than two of these models: Coding, Agents & tools, Maths, Instruction following, Long context, Human preference.

Model, click to add or removeIndex

Where sources disagree

Across the 3 benchmarks both have, GPT-5.5 leads 2, GPT-5 Pro leads 1.

Overall indexGPT-5.5 (xhigh)GPT-5 ProLeader
BenchLeader Index64.159.6neck 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. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.

MeasureGPT-5.5 (xhigh)GPT-5 Pro
Blended price per 1M tokens$11.25$41.25
Input / output per 1M$5.00 / $30.00$15.00 / $120.00
Cached input per 1M$0.500–
Price per task: chat reply$0.011$0.042
Price per task: summarize a 30-page report$0.078$0.252
Price per task: code edit$0.075$0.270
Price per task: agentic coding session$0.420$1.38
Price per task: structured extraction$0.016$0.054
Agentic coding session, input mostly cached$0.217–
Output speed81 tok/s–
Time to first answer38.3 s–
Time to a complete answer, last measured 13 Nov 2026104.3 s–

Each model is compared at its best-ranked reasoning-effort setting. GPT-5.5 (xhigh) scores 64.1 and takes 38 s to its first answer token; GPT-5.5 (high) scores 63.5 in 16 s, GPT-5.5 scores 61.0 in 3 s. GPT-5 Pro scores 59.6. 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

140 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-5.5 (xhigh)GPT-5 Pro
BenchLeader IndexBenchLeader64.159.6
Agents & tools scoreBenchLeader61.8–
Coding scoreBenchLeader60.7–
Instruction following scoreBenchLeader74.0–
Knowledge scoreBenchLeader63.666.1
Long context scoreBenchLeader66.9–
Maths scoreBenchLeader69.3–
Multimodal scoreBenchLeader62.367.4
Reasoning scoreBenchLeader68.155.0
Blended price $/MBenchLeader$11.25$41.25
Output speedBenchLeader81 tok/s–
Time to first answerBenchLeader38.3 s–
Context windowBenchLeader1,050,000 tokens400,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub90.7%†–
Humanity's Last ExamScale AI / CAIS–31.6%
SimpleBenchSimpleBench69.0%†61.6%
Arena Hard PromptsArena (LMArena)1499†–
LiveBench 1.0 ReasoningLiveBench89.7%–
GPQA Diamond (AA)Artificial Analysis93.5%–
Humanity's Last Exam (AA)Artificial Analysis45.8%–
GPQA Diamond (Vals)Vals AI93.2%–
Kagi LLM BenchmarkKagi LLM Benchmark88.8%†76.8%
ARC-AGI-1ARC Prize95.0%70.2%
ARC-AGI-2ARC Prize85.0%18.3%
ARC-AGI-3ARC Prize0.4%†–
CritPtArtificial Analysis27.1%–
Arena ExpertArena (LMArena)1510†–
Chess PuzzlesEpoch AI Benchmarking Hub63.0%48.0%†
Mystery Game PuzzlesEpoch AI Benchmarking Hub56.0%–
CL-bench LifeEpoch AI Benchmarking Hub22.2%†–
LMCAEpoch AI Benchmarking Hub54.3%–
DTBenchEpoch AI Benchmarking Hub96.0%–
ForecastBenchForecastBench64.2%†–
BTF-3Epoch AI Benchmarking Hub14.3%†–
Coding
SciCodeSciCode55.8%–
WeirdMLWeirdML84.9%60.4%†
FrontierCodeCognition43.0%†–
GSO-BenchGSO-Bench40.2%–
Show all 140 benchmarks
MetricPublisherGPT-5.5 (xhigh)GPT-5 Pro
Coding
Arena CodingArena (LMArena)1510†–
Arena WebDevArena (LMArena)1512–
LiveBench 1.0 CodingLiveBench82.2%–
LiveCodeBenchVals AI85.3%–
SWE-bench (Vals)Vals AI82.6%–
Code MigrationVals AI45.2%–
ProgramBenchVals AI0.5%–
Vibe Code Bench v1.1Vals AI69.8%–
SWE Atlas v1.0: Codebase QnAScale AI SEAL45.4%–
SWE Atlas v1.0: RefactoringScale AI SEAL44.8%–
SWE Atlas v1.0: Test WritingScale AI SEAL42.6%–
MirrorCodeEpoch AI Benchmarking Hub23.3%–
Surface Evolver BenchEpoch AI Benchmarking Hub88.1%†–
DeepSWE v1.1Epoch AI Benchmarking Hub67.0%–
ALE-BenchEpoch AI Benchmarking Hub1943.0–
AlgoTuneAlgoTune–1.3†
Terminal-Bench 4.0 (AA)Artificial Analysis14.7%–
Terminal-Bench 2.1 (AA)Artificial Analysis84.3%–
GameBench 2 OverallDuelLab GameBench 249.2†–
GameBench 2 by reasoning settingDuelLab GameBench 259.9–
Design Arena WebsiteDesign Arena1248†–
Agents & tools
Terminal-BenchTerminal-Bench84.7%†–
OSWorld-Verified 2.0OSWorld13.0%–
Remote Labor IndexScale AI / CAIS6.3%†–
APEX-AgentsMercor55.1%†–
LiveBench Agentic CodingLiveBench54.0%–
Terminal-Bench HardArtificial Analysis60.6%–
τ²-Bench Telecom (AA)Artificial Analysis93.9%–
Terminal-Bench 2.1 (Vals)Vals AI57.3%†–
MCP AtlasScale AI SEAL75.3%–
HiL-BenchScale AI SEAL39.7%†–
τ³-bench Bankingτ²-bench44.6%–
GDPval-AA v2.1Artificial Analysis1357–
τ³-Banking (AA)Artificial Analysis39.0%–
ITBench SRE (AA)Artificial Analysis45.8%–
Analyst Agent (AA)Artificial Analysis50.0%–
APEX-Agents (AA)Artificial Analysis37.7%–
Finance Agent v2Vals AI51.8%–
Harvey's Legal Agent Benchmark v1Vals AI3.8%–
Legal Research BenchVals AI40.4%–
SkillsBenchVals AI62.2%–
SREBenchVals AI3.8%–
Tax Agent BenchVals AI21.8%–
Terminal-Bench 2.0 (Vals)Vals AI73.2%†–
Time Horizon Index: KSPVals AI8.3%–
Arena SearchArena (LMArena)1226†–
DeepResearch BenchDeepResearch Bench54.0%†–
PostTrainBenchEpoch AI Benchmarking Hub23.9%–
ExploitBenchEpoch AI Benchmarking Hub47.4%†–
GBAEvalEpoch AI Benchmarking Hub53.2%†–
Vending-Bench 2Andon Labs7523.8†–
AutomationBenchArtificial Analysis47.3%–
GDP.pdf (AA)Artificial Analysis21.2%–
EnterpriseOps-GymArtificial Analysis46.6%–
AA-Briefcase v1.1Artificial Analysis1135–
Design Arena AgenticDesign Arena1113†–
RoboDojo (LLM as robot policy)RoboDojo1.1†–
DeepSearchQAGoogle–65.2%
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub85.3%55.8%†
FrontierMath Tier 4Epoch AI Benchmarking Hub72.5%19.5%†
OTIS Mock AIMEEpoch AI Benchmarking Hub84.4%†–
ProofBenchVals AI50.0%–
LiveBench MathematicsLiveBench95.9%–
AIME 2026MathArena100.0%–
HMMT February 2026MathArena98.5%–
USAMO 2026MathArena98.2%–
MathArena ApexMathArena80.2%–
Arena MathsArena (LMArena)1500†–
FrontierMath ErdősEpoch AI Benchmarking Hub0.0%–
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub63.0%–
LiveBench 1.0 Data AnalysisLiveBench81.6%–
MMLU-ProVals AI88.1%–
LegalBenchVals AI86.5%–
CorpFinVals AI68.4%–
TaxEvalVals AI75.0%–
PRBench FinanceScale AI SEAL–51.1%
PRBench LegalScale AI SEAL–49.9%
MultiNRCScale AI SEAL–65.2%
CaseLaw v2Vals AI66.2%–
Excel Modeling BenchmarkVals AI64.5%–
MedCodeVals AI49.1%–
MedScribeVals AI86.9%–
Public Benefits Bench v1.1Vals AI60.9%–
DrugDiscoveryBenchScale AI SEAL51.6%–
EBR-benchEpoch AI Benchmarking Hub34.3%–
GDP.pdfEpoch AI Benchmarking Hub26.0%–
Instruction following
LiveBench LanguageLiveBench87.4%–
LiveBench Instruction FollowingLiveBench70.7%–
IFBenchArtificial Analysis75.8%–
Arena Instruction FollowingArena (LMArena)1475†–
Human preference
Arena TextArena (LMArena)1476†–
EQ-Bench 4EQ-Bench1295†–
EQ-Bench Creative Writing v3EQ-Bench1845†–
Arena Creative WritingArena (LMArena)1448†–
Arena Multi-turnArena (LMArena)1484†–
Arena Longer QueriesArena (LMArena)1486†–
Multimodal
Arena VisionArena (LMArena)1296†–
MMMU-ProArtificial Analysis79.9%–
VISTAScale AI SEAL–52.4%
MMMU-Pro (Vals)Vals AI88.3%–
MortgageTaxVals AI68.8%–
Blueprint-Bench 2Epoch AI Benchmarking Hub36.2%†–
Furniture AssemblyEpoch AI Benchmarking Hub44.2%–
Code2Video-AAArtificial Analysis1000–
Long context
AA-LCR v1.1Artificial Analysis84.3%–
Arena DocumentArena (LMArena)1479†–
MLCRArtificial Analysis28.9%–
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub160.1†151.2
LiveBench 1.0LiveBench80.2%–
AA Intelligence Index v4.3.2Artificial Analysis38.4–
AA Progress Index v1Artificial Analysis320–
Vals RSI IndexVals AI16.5%–
Vals Multimodal IndexVals AI68.1%–
Safety & honesty
FORTRESSScale AI SEAL16.3%15.2%
MASKScale AI SEAL–86.0%

Data as of 2026-11-16. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261111-7b598bb13de4 (https://benchmarks.duellab.org/releases/gb2-20261111-7b598bb13de4/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.

What changed

  • GPT-5.5 (xhigh): 1 new result (GDPval-AA v2.1).
  • GPT-5.5 (xhigh): BenchLeader Index 64.6 → 64.1.
  • GPT-5.5 (xhigh): 1 score revision.
  • GPT-5 Pro: BenchLeader Index 60.2 → 59.6.
  • GPT-5.5 (xhigh): 1 new result (MirrorCode).
  • GPT-5.5 (xhigh): 1 score revision.
  • GPT-5.5 (xhigh): 1 new result (AA Progress Index v1).
  • GPT-5.5 (xhigh): cost per task moved from $2.63/M to $2.10/M (20% down).
  • GPT-5.5 (xhigh): 1 new result (AA-Briefcase v1.1).
  • GPT-5.5 (xhigh): 2 new results (Harvey's Legal Agent Benchmark v1, Vals RSI Index).

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

GPT-5.5 vs GPT-5 Pro: questions

Is GPT-5.5 better than GPT-5 Pro?
GPT-5.5 (xhigh) and GPT-5 Pro are neck and neck on quality (64.1 vs 59.6, within the ±7.5 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 16 Nov 2026, so check the category scores for your use.
GPT-5.5 vs GPT-5 Pro: which is cheaper, and will that change?
GPT-5.5 is cheaper today: $11.25 against $41.25 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?
GPT-5.5 accepts more context: 1,050,000 against 400,000 tokens for GPT-5 Pro.
Do independent benchmarks agree on GPT-5.5 vs GPT-5 Pro?
Across the 3 benchmarks both have, GPT-5.5 leads 2, GPT-5 Pro leads 1.
When was GPT-5.5 released?
GPT-5.5 was released on 23 Apr 2026.