Enter opens the highlighted result. Esc closes.

GPT-5.2 vs GPT-5.5

Updated October 21, 2026. 97 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace GPT-5.2 Replace GPT-5.5
GPT-5.2OpenAI
Coding
58.9
Overall
30.4
Output $/M
$14.00
6
GPT-5.5OpenAI
Coding
67.8
Overall
38.4
Output $/M
$30.00
91
vs boards won of 97 shared

Decision reading

Pick GPT-5.5 for coding: it scores 67.8 on the Vibe Coding Index against 58.9 for GPT-5.2.

Pick GPT-5.2 when output tokens cost 2.1x less, or when what matters is LiveCodeBench (Vals AI) or GPQA Diamond (Epoch AI run), where it leads.

Model AGPT-5.2OpenAI58.9/1002 independent benchmarks$1.91 per solved taskModel BGPT-5.5OpenAI67.8/1002 independent benchmarks$1.65 per solved task
Shared results
97
GPT-5.2 only
14
GPT-5.5 only
35
Like-for-like categories
8 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

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-5.2 58.9 from 2 benchmarks, GPT-5.5 67.8 from 2 benchmarks.
Widest category
Math, 20.4 points apart on average over 6 shared benchmarks.
Widest single gap
FrontierMath, tier 4: GPT-5.2 31.7% against GPT-5.5 72.5%, 40.8 points apart on a 0 to 100 scale.
Output price
GPT-5.2 $14.00 against GPT-5.5 $30.00 per million output tokens, 2.1x apart.
Context window
GPT-5.2 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-5.2BarsGPT-5.5Ties
Coding111
Intelligence02
Agentic work09
Reasoning115
Math15
Knowledge210
Web design08
General131
All shared boards691
CodingLike-for-likeFour of these boards feed the Vibe Coding Index111
Coding benchmarks for GPT-5.2 and GPT-5.5
BenchmarkGPT-5.2GPT-5.5Leader
SWE-bench Verified72.8%Not measuredOnly GPT-5.2 measured
SWE-bench Multilingual66.7%Not measuredOnly GPT-5.2 measured
LiveBench codingNot measured85.1%Only GPT-5.5 measured
LMArena WebDev14171513GPT-5.5
AA Coding IndexNot measured74.9Only GPT-5.5 measured
LiveCodeBench (Vals AI)85.4%85.3%GPT-5.2
SWE-bench Verified (Vals AI)75.8%82.6%GPT-5.5
Vibe Code Bench (Vals AI)53.5%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)89.4%Not measuredOnly GPT-5.2 measured
SciCodeNot measured56.1%Only GPT-5.5 measured
Terminal-Bench Hard (Artificial Analysis run)47.0%60.6%GPT-5.5
Terminal-Bench64.9%84.7%GPT-5.5
FrontierCodeNot measured43.0%Only GPT-5.5 measured
GSO-Bench27.5%40.2%GPT-5.5
WeirdML72.2%84.9%GPT-5.5
MirrorCodeNot measured10.0%Only GPT-5.5 measured
ALE-Bench1293.51943.0GPT-5.5
LMArena Text: coding14421494GPT-5.5
LMArena Text: software and IT14341493GPT-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
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-5.2 and GPT-5.5
BenchmarkGPT-5.2GPT-5.5Leader
AA Intelligence Index30.438.4GPT-5.5
Epoch Capabilities Index153.7159.7GPT-5.5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index09
Agentic work benchmarks for GPT-5.2 and GPT-5.5
BenchmarkGPT-5.2GPT-5.5Leader
AA Agentic IndexNot measured36.4Only GPT-5.5 measured
Design Arena: agents building web apps10861117GPT-5.5
Design Arena: agents building full-stack apps10431089GPT-5.5
Design Arena: agents building mobile apps10941143GPT-5.5
Design Arena: agents building Android apps10641169GPT-5.5
Design Arena: agents building Godot games11421173GPT-5.5
Design Arena: agents building gamesNot measured1179Only GPT-5.5 measured
Design Arena: HTML slidesNot measured1067Only GPT-5.5 measured
Design Arena: PowerPoint slidesNot measured1108Only 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 Telecom84.8%93.9%GPT-5.5
APEX-AgentsNot measured55.1%Only GPT-5.5 measured
METR time horizons75.3%Not measuredOnly GPT-5.2 measured
Remote Labor Index2.5%6.3%GPT-5.5
GDPval49.7%Not measuredOnly GPT-5.2 measured
OSWorld 2.0Not measured13.0%Only GPT-5.5 measured
DeepResearch Bench41.1%54.0%GPT-5.5
PostTrainBenchNot measured27.2%Only GPT-5.5 measured
Vending-Bench 2$3,591$7,524GPT-5.5
Neither model has a result on the other 12 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index115
Reasoning benchmarks for GPT-5.2 and GPT-5.5
BenchmarkGPT-5.2GPT-5.5Leader
GPQA Diamond91.7%93.2%GPT-5.5
LiveBench reasoningNot measured89.7%Only GPT-5.5 measured
MMMU Pro (Vals AI)86.7%88.3%GPT-5.5
GPQA Diamond (Artificial Analysis run)90.3%93.5%GPT-5.5
Humanity's Last Exam (Artificial Analysis run)37.7%45.8%GPT-5.5
GPQA Diamond (Epoch AI run)91.4%90.7%GPT-5.2
ARC-AGI86.2%95.0%GPT-5.5
ARC-AGI-252.9%85.0%GPT-5.5
SimpleBench45.8%69.0%GPT-5.5
Chess puzzles48.0%63.0%GPT-5.5
Mystery game puzzles23.0%56.0%GPT-5.5
EBR-bench23.0%34.3%GPT-5.5
VPCT84.0%Not measuredOnly GPT-5.2 measured
LMArena Text: hard prompts14281489GPT-5.5
LMArena Text: expert14451507GPT-5.5
LMArena Text: hard prompts in English14311483GPT-5.5
LMArena Vision: diagrams12651325GPT-5.5
LMArena Vision: homework12761332GPT-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-5.2 and GPT-5.5
BenchmarkGPT-5.2GPT-5.5Leader
AIME96.9%Not measuredOnly GPT-5.2 measured
MGSM (Vals AI)94.0%Not measuredOnly GPT-5.2 measured
AA Math Index99.0Not measuredOnly GPT-5.2 measured
AIME 2025 (Artificial Analysis run)99.0%Not measuredOnly GPT-5.2 measured
OTIS Mock AIME96.1%84.4%GPT-5.2
FrontierMath, tiers 1 to 367.4%85.3%GPT-5.5
FrontierMath, tier 431.7%72.5%GPT-5.5
ProofBench15.0%50.0%GPT-5.5
LMArena Text: math14401487GPT-5.5
LMArena Text: mathematical work14421496GPT-5.5
Neither model has a result on the other 3 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index210
Knowledge benchmarks for GPT-5.2 and GPT-5.5
BenchmarkGPT-5.2GPT-5.5Leader
MMLU Pro86.2%88.1%GPT-5.5
LegalBench (Vals AI)82.8%86.5%GPT-5.5
CaseLaw (Vals AI)66.0%66.2%GPT-5.5
CorpFin (Vals AI)65.9%68.4%GPT-5.5
TaxEval (Vals AI)75.8%75.0%GPT-5.2
MortgageTax (Vals AI)67.1%68.8%GPT-5.5
MedQA (Vals AI)94.1%Not measuredOnly GPT-5.2 measured
MedCode (Vals AI)49.8%49.1%GPT-5.2
MMLU Pro (Artificial Analysis run)87.4%Not measuredOnly GPT-5.2 measured
SimpleQA Verified37.1%63.0%GPT-5.5
LMArena Text: science14251485GPT-5.5
LMArena Text: medicine and healthcare14251465GPT-5.5
LMArena Text: legal and government14271491GPT-5.5
LMArena Text: business and finance14141478GPT-5.5
Neither model has a result on the other 3 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index08
Web design benchmarks for GPT-5.2 and GPT-5.5
BenchmarkGPT-5.2GPT-5.5Leader
Design Arena: websites11961256GPT-5.5
Design Arena: UI components11901260GPT-5.5
Design Arena: game dev11961294GPT-5.5
Design Arena: data viz12021265GPT-5.5
Design Arena: 3D10791198GPT-5.5
Design Arena: all code categories11711260GPT-5.5
Design Arena: SVG11371234GPT-5.5
Design Arena: ASCII art11531254GPT-5.5
LiveBench designNot measured70.3%Only GPT-5.5 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index131
General benchmarks for GPT-5.2 and GPT-5.5
BenchmarkGPT-5.2GPT-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)49.3%51.5%GPT-5.5
MedScribe (Vals AI)84.4%86.9%GPT-5.5
Vals Multimodal IndexNot measured68.1%Only GPT-5.5 measured
IFBench75.4%75.9%GPT-5.5
Long context reasoning (AA-LCR)82.7%84.3%GPT-5.5
DTBench90.9%96.0%GPT-5.5
LMCA43.9%54.3%GPT-5.5
CL-bench18.2%Not measuredOnly GPT-5.2 measured
Surface Evolver BenchNot measured88.1%Only GPT-5.5 measured
Furniture assembly38.3%44.2%GPT-5.5
ExploitBenchNot measured47.4%Only GPT-5.5 measured
CL-bench LifeNot measured22.2%Only GPT-5.5 measured
LMArena Text14161471GPT-5.5
LMArena Text: instruction following14091478GPT-5.5
LMArena Text: creative writing13761455GPT-5.5
LMArena Vision12461297GPT-5.5
LMArena Text: English14221470GPT-5.5
LMArena Text: non-English14051467GPT-5.5
LMArena Text: Chinese14471534GPT-5.5
LMArena Text: German14441480GPT-5.5
LMArena Text: Japanese14201499GPT-5.5
LMArena Text: Korean13741460GPT-5.5
LMArena Text: French14541485GPT-5.5
LMArena Text: Spanish14131468GPT-5.5
LMArena Text: Russian14151473GPT-5.5
LMArena Text: Polish14261465GPT-5.5
LMArena Text: multi-turn14191476GPT-5.5
LMArena Text: longer queries14131484GPT-5.5
LMArena Text: writing and language13921466GPT-5.5
LMArena Text: entertainment and media13781449GPT-5.5
LMArena Vision: English12431292GPT-5.5
LMArena Vision: Chinese13051360GPT-5.5
LMArena Vision: reading text12571306GPT-5.5
LMArena Vision: humor12271293GPT-5.5
LMArena Vision: captioning1267Not measuredOnly GPT-5.2 measured
LMArena Vision: recognizing things12321231GPT-5.2
LMArena Vision: creative writing12251301GPT-5.5
LMArena Document14051486GPT-5.5
Neither model has a result on the other 6 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-5.2 and GPT-5.5
BenchmarkGPT-5.2GPT-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-5.2$0.0088Fits in one request
GPT-5.5$0.020Fits in one request

GPT-5.2 costs less

Repository review

50K input + 3K output tokens

GPT-5.2$0.130Fits in one request
GPT-5.5$0.340Fits in one request

GPT-5.2 costs less

Agent loop

200K input + 10K output tokens

GPT-5.2$0.490Fits in one request
GPT-5.5$1.30Fits in one request

GPT-5.2 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-5.2 and GPT-5.5
SpecificationOpenAI GPT-5.2OpenAI GPT-5.5
MakerOpenAIOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedDecember 10, 2025April 24, 2026
Context window400K1.05M
Input $/Mtok$1.75$5.00
Output $/Mtok$14.00$30.00
Coding index58.967.8
Independent measurements behind it22
Cost per solved task$1.91$1.65
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-5.2 better than GPT-5.5 for coding?

Pick GPT-5.5 for coding: it scores 67.8 on the Vibe Coding Index against 58.9 for GPT-5.2. Pick GPT-5.2 when output tokens cost 2.1x less, or when what matters is LiveCodeBench (Vals AI) or GPQA Diamond (Epoch AI run), where it leads.

Which is cheaper, GPT-5.2 or GPT-5.5?

GPT-5.2 costs $1.75 per million input tokens and $14.00 per million output tokens; GPT-5.5 costs $5.00 and $30.00. Per solved SWE-bench Verified task, GPT-5.2 costs $1.91 and GPT-5.5 $1.65.

Which has the bigger context window, GPT-5.2 or GPT-5.5?

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

How many benchmarks is the GPT-5.2 vs GPT-5.5 comparison based on?

97 benchmarks have a result for both models as of October 21, 2026. GPT-5.2's coding index rests on 2 independent benchmarks and GPT-5.5's on 2. 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-5-2-vs-gpt-5-5" title="GPT-5.2 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-5-2-vs-gpt-5-5">LLMBenchmark.ai, GPT-5.2 vs GPT-5.5</a></p>