Enter opens the highlighted result. Esc closes.

GPT-5 vs GPT-5.5

GPT-5.5 leads GPT-5 on coding, 71.3 to 38.8 on the Vibe Coding Index, and GPT-5 costs 3.0x less per output token ($10.00 vs $30.00 per million). Updated October 21, 2026; 92 benchmarks have a result for both.

Replace GPT-5 Replace GPT-5.5
GPT-5OpenAI
Coding
38.8
Overall
51.5
Output $/M
$10.00
5
GPT-5.5OpenAI
Coding
71.3
Overall
69.2
Output $/M
$30.00
87
vs boards won of 92 shared

GPT-5 or GPT-5.5: which to pick

Pick GPT-5.5 for coding: it scores 71.3 on the Vibe Coding Index against 38.8 for GPT-5.

Pick GPT-5 for output tokens 3.0x cheaper ($10.00 vs $30.00 per million) and a lower cost per solved task ($0.39 against $1.65).

Model AGPT-5OpenAI38.8/1003 independent benchmarks$0.39 per solved taskModel BGPT-5.5OpenAI71.3/1005 independent benchmarks$1.65 per solved task
Shared results
92
GPT-5 only
21
GPT-5.5 only
42
Like-for-like categories
8 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
GPT-5 38.8 from 3 benchmarks, GPT-5.5 71.3 from 5 benchmarks.
Widest category
Math, 24.6 points apart on average over 6 shared benchmarks.
Widest single gap
ARC-AGI-2: GPT-5 9.9% against GPT-5.5 85.0%, 75.1 points apart on a 0 to 100 scale.
Output price
GPT-5 $10.00 against GPT-5.5 $30.00 per million output tokens, 3.0x apart.
Context window
GPT-5 takes 400K tokens, GPT-5.5 1.05M.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryGPT-5BarsGPT-5.5Ties
Coding112
Intelligence02
Agentic work03
Reasoning017
Math15
Knowledge211
Web design08
General129
All shared boards587
CodingLike-for-likeSix of these boards feed the Vibe Coding Index112
Coding benchmarks for GPT-5 and GPT-5.5
BenchmarkGPT-5GPT-5.5Leader
Aider polyglot88.0%Not measuredOnly GPT-5 measured
SWE-bench Verified74.4%Not measuredOnly GPT-5 measured
LiveBench codingNot measured85.1%Only GPT-5.5 measured
LMArena WebDev14181513GPT-5.5
AA Coding Index37.874.9GPT-5.5
LiveCodeBench (Vals AI)85.9%85.3%GPT-5
SWE-bench Verified (Vals AI)69.0%82.6%GPT-5.5
Vibe Code Bench (Vals AI)20.1%69.8%GPT-5.5
Code migration (Vals AI)Not measured45.2%Only GPT-5.5 measured
ProgramBench (Vals AI)Not measured0.5%Only GPT-5.5 measured
Terminal-Bench 2.1 (Vals AI)Not measured76.4%Only GPT-5.5 measured
SkillsBench (Vals AI)Not measured62.5%Only GPT-5.5 measured
LiveCodeBench (Artificial Analysis run)84.6%Not measuredOnly GPT-5 measured
SciCodeNot measured56.1%Only GPT-5.5 measured
Terminal-Bench Hard (Artificial Analysis run)37.9%60.6%GPT-5.5
Terminal-Bench49.6%84.7%GPT-5.5
FrontierCodeNot measured43.0%Only GPT-5.5 measured
GSO-Bench6.9%40.2%GPT-5.5
WeirdML60.7%84.9%GPT-5.5
MirrorCodeNot measured10.0%Only GPT-5.5 measured
ALE-Bench807.61943.0GPT-5.5
LMArena Text: coding14361494GPT-5.5
LMArena Text: software and IT14201493GPT-5.5
LMArena WebDev: ReactNot measured1506Only GPT-5.5 measured
LMArena WebDev: HTML14271543GPT-5.5
LMArena WebDev: from an imageNot measured1532Only GPT-5.5 measured
SciCode0.0%Not measuredOnly GPT-5 measured
Neither model has a result on the other 12 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for GPT-5 and GPT-5.5
BenchmarkGPT-5GPT-5.5Leader
AA Intelligence Index23.038.4GPT-5.5
Epoch Capabilities Index150.0159.7GPT-5.5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index03
Agentic work benchmarks for GPT-5 and GPT-5.5
BenchmarkGPT-5GPT-5.5Leader
AA Agentic IndexNot measured36.4Only GPT-5.5 measured
Design Arena: agents building web appsNot measured1117Only GPT-5.5 measured
Design Arena: agents building full-stack appsNot measured1089Only GPT-5.5 measured
Design Arena: agents building mobile appsNot measured1143Only GPT-5.5 measured
Design Arena: agents building Android appsNot measured1163Only GPT-5.5 measured
Design Arena: agents building Godot gamesNot measured1173Only GPT-5.5 measured
Design Arena: agents building gamesNot measured1179Only GPT-5.5 measured
Design Arena: HTML slidesNot measured1067Only GPT-5.5 measured
Design Arena: PowerPoint slidesNot measured1109Only GPT-5.5 measured
LiveBench researchNot measured61.6%Only GPT-5.5 measured
LiveBench browserNot measured48.0%Only GPT-5.5 measured
LiveBench long agenticNot measured44.6%Only GPT-5.5 measured
SREBench (Vals AI)Not measured3.8%Only GPT-5.5 measured
Finance Agent (Vals AI)Not measured51.8%Only GPT-5.5 measured
Tax Agent Bench (Vals AI)Not measured21.8%Only GPT-5.5 measured
Legal Research Bench (Vals AI)Not measured40.4%Only GPT-5.5 measured
Excel Modeling Benchmark (Vals AI)Not measured64.5%Only GPT-5.5 measured
Time Horizon Index (Vals AI)Not measured8.3%Only GPT-5.5 measured
τ²-Bench Telecom86.5%93.9%GPT-5.5
APEX-AgentsNot measured55.1%Only GPT-5.5 measured
METR time horizons69.6%Not measuredOnly GPT-5 measured
Remote Labor Index1.7%6.3%GPT-5.5
GDPval34.8%Not measuredOnly GPT-5 measured
OSWorld 2.0Not measured13.0%Only GPT-5.5 measured
BALROG32.8%Not measuredOnly GPT-5 measured
DeepResearch Bench49.6%54.0%GPT-5.5
PostTrainBenchNot measured27.2%Only GPT-5.5 measured
Vending-Bench 2Not measured$7,524Only GPT-5.5 measured
BrowseComp-Plus80.0%Not measuredOnly GPT-5 measured
Neither model has a result on the other 12 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index017
Reasoning benchmarks for GPT-5 and GPT-5.5
BenchmarkGPT-5GPT-5.5Leader
GPQA Diamond85.6%93.2%GPT-5.5
LiveBench reasoningNot measured89.7%Only GPT-5.5 measured
MMMU Pro (Vals AI)81.5%88.3%GPT-5.5
GPQA Diamond (Artificial Analysis run)85.4%93.5%GPT-5.5
Humanity's Last Exam (Artificial Analysis run)28.5%45.8%GPT-5.5
GPQA Diamond (Epoch AI run)86.2%90.7%GPT-5.5
ARC-AGI65.7%95.0%GPT-5.5
ARC-AGI-29.9%85.0%GPT-5.5
SimpleBench56.7%69.0%GPT-5.5
Chess puzzles36.0%63.0%GPT-5.5
Mystery game puzzles23.0%56.0%GPT-5.5
EBR-bench12.7%34.3%GPT-5.5
VPCT66.0%Not measuredOnly GPT-5 measured
LMArena Text: hard prompts14151489GPT-5.5
LMArena Text: expert14191507GPT-5.5
LMArena Text: hard prompts in English14191483GPT-5.5
LMArena Vision: diagrams12521325GPT-5.5
LMArena Vision: homework12781332GPT-5.5
Kagi LLM Benchmark72.7%88.8%GPT-5.5
Neither model has a result on the other 3 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index15
Math benchmarks for GPT-5 and GPT-5.5
BenchmarkGPT-5GPT-5.5Leader
AIME93.4%Not measuredOnly GPT-5 measured
MATH 500 (Vals AI)96.0%Not measuredOnly GPT-5 measured
MGSM (Vals AI)92.8%Not measuredOnly GPT-5 measured
AA Math Index94.3Not measuredOnly GPT-5 measured
AIME 2025 (Artificial Analysis run)94.3%Not measuredOnly GPT-5 measured
OTIS Mock AIME91.4%84.4%GPT-5
FrontierMath, tiers 1 to 355.4%85.3%GPT-5.5
FrontierMath, tier 422.0%72.5%GPT-5.5
ProofBench18.0%50.0%GPT-5.5
MATH level 598.1%Not measuredOnly GPT-5 measured
LMArena Text: math14071487GPT-5.5
LMArena Text: mathematical work14051496GPT-5.5
Neither model has a result on the other 1 board here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index211
Knowledge benchmarks for GPT-5 and GPT-5.5
BenchmarkGPT-5GPT-5.5Leader
MMLU Pro86.5%88.1%GPT-5.5
LegalBench (Vals AI)86.0%86.5%GPT-5.5
CaseLaw (Vals AI)66.5%66.2%GPT-5
CorpFin (Vals AI)61.1%68.4%GPT-5.5
TaxEval (Vals AI)73.4%75.0%GPT-5.5
MortgageTax (Vals AI)65.5%68.8%GPT-5.5
MedQA (Vals AI)96.3%Not measuredOnly GPT-5 measured
MedCode (Vals AI)49.6%49.1%GPT-5
MMLU Pro (Artificial Analysis run)87.1%Not measuredOnly GPT-5 measured
SimpleQA Verified50.1%63.0%GPT-5.5
GeoBench81.0%Not measuredOnly GPT-5 measured
LMArena Text: science14161485GPT-5.5
LMArena Text: medicine and healthcare14131465GPT-5.5
LMArena Text: legal and government14311491GPT-5.5
LMArena Text: business and finance14001478GPT-5.5
FACTS Benchmark Suite56.5%66.7%GPT-5.5
Neither model has a result on the other 2 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index08
Web design benchmarks for GPT-5 and GPT-5.5
BenchmarkGPT-5GPT-5.5Leader
Design Arena: websites11841256GPT-5.5
Design Arena: UI components11801260GPT-5.5
Design Arena: game dev11851294GPT-5.5
Design Arena: data viz12211265GPT-5.5
Design Arena: 3D10561198GPT-5.5
Design Arena: all code categories11681260GPT-5.5
Design Arena: SVG11891234GPT-5.5
Design Arena: ASCII art11411255GPT-5.5
LiveBench designNot measured70.3%Only GPT-5.5 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index129
General benchmarks for GPT-5 and GPT-5.5
BenchmarkGPT-5GPT-5.5Leader
LiveBench data analysisNot measured81.6%Only GPT-5.5 measured
Public Benefits Bench (Vals AI)Not measured60.9%Only GPT-5.5 measured
SAGE (Vals AI)43.7%51.5%GPT-5.5
MedScribe (Vals AI)83.7%86.9%GPT-5.5
Vals Multimodal IndexNot measured68.1%Only GPT-5.5 measured
IFBench73.1%75.9%GPT-5.5
Long context reasoning (AA-LCR)78.2%84.3%GPT-5.5
DTBench90.7%96.0%GPT-5.5
LMCA40.0%54.3%GPT-5.5
Fiction.LiveBench97.2%Not measuredOnly GPT-5 measured
Creative writing (Lech Mazur)86.0%Not measuredOnly GPT-5 measured
Surface Evolver BenchNot measured88.1%Only GPT-5.5 measured
Furniture assemblyNot measured44.2%Only GPT-5.5 measured
ExploitBenchNot measured47.4%Only GPT-5.5 measured
CL-bench LifeNot measured22.2%Only GPT-5.5 measured
LMArena Text14061471GPT-5.5
LMArena Text: instruction following13881478GPT-5.5
LMArena Text: creative writing13651455GPT-5.5
LMArena Vision12321297GPT-5.5
LMArena Text: English14091470GPT-5.5
LMArena Text: non-English13971467GPT-5.5
LMArena Text: Chinese14221534GPT-5.5
LMArena Text: German14161480GPT-5.5
LMArena Text: Japanese14091499GPT-5.5
LMArena Text: Korean13601460GPT-5.5
LMArena Text: French14091485GPT-5.5
LMArena Text: Spanish13991468GPT-5.5
LMArena Text: Russian14071473GPT-5.5
LMArena Text: Polish14311465GPT-5.5
LMArena Text: multi-turn14261476GPT-5.5
LMArena Text: longer queries13991484GPT-5.5
LMArena Text: writing and language13841466GPT-5.5
LMArena Text: entertainment and media13791449GPT-5.5
LMArena Vision: English12311292GPT-5.5
LMArena Vision: Chinese12671360GPT-5.5
LMArena Vision: reading text12461306GPT-5.5
LMArena Vision: humor12191293GPT-5.5
LMArena Vision: captioning1212Not measuredOnly GPT-5 measured
LMArena Vision: recognizing things12631231GPT-5
LMArena Vision: creative writing12101301GPT-5.5
LMArena DocumentNot measured1486Only GPT-5.5 measured
Neither model has a result on the other 5 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-5 and GPT-5.5
BenchmarkGPT-5GPT-5.5Leader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

GPT-5$0.0063Fits in one request
GPT-5.5$0.020Fits in one request

GPT-5 costs less

Repository review

50K input + 3K output tokens

GPT-5$0.092Fits in one request
GPT-5.5$0.340Fits in one request

GPT-5 costs less

Agent loop

200K input + 10K output tokens

GPT-5$0.350Fits in one request
GPT-5.5$1.30Fits in one request

GPT-5 costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of GPT-5 and GPT-5.5
SpecificationOpenAI GPT-5OpenAI GPT-5.5
MakerOpenAIOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedAugust 7, 2025April 24, 2026
Context window400K1.05M
Input $/Mtok$1.25$5.00
Output $/Mtok$10.00$30.00
Coding index38.871.3
Independent measurements behind it35
Cost per solved task$0.39$1.65
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-5 better than GPT-5.5 for coding?

Pick GPT-5.5 for coding: it scores 71.3 on the Vibe Coding Index against 38.8 for GPT-5. Pick GPT-5 for output tokens 3.0x cheaper ($10.00 vs $30.00 per million) and a lower cost per solved task ($0.39 against $1.65).

Which is cheaper, GPT-5 or GPT-5.5?

GPT-5 costs $1.25 per million input tokens and $10.00 per million output tokens; GPT-5.5 costs $5.00 and $30.00. Per solved SWE-bench Verified task, GPT-5 costs $0.39 and GPT-5.5 $1.65.

Which has the bigger context window, GPT-5 or GPT-5.5?

GPT-5.5, with 1.05M tokens against 400K.

How many benchmarks is the GPT-5 vs GPT-5.5 comparison based on?

92 benchmarks have a result for both models as of October 21, 2026. GPT-5's coding index rests on 3 independent benchmarks and GPT-5.5's on 5. Where only one model has a result, the page says so instead of naming a winner.

Compare next

Embed this comparison on your site

Free under CC BY 4.0, while the source link stays visible. Preview the frame · Terms and other embeds

<iframe src="https://llmbenchmark.ai/embed/compare/gpt-5-vs-gpt-5-5" title="GPT-5 vs GPT-5.5, LLMBenchmark.ai" width="100%" height="360" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/compare/gpt-5-vs-gpt-5-5">LLMBenchmark.ai, GPT-5 vs GPT-5.5</a></p>