LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Claude Sonnet 5.5 vs GPT-5.4

Updated October 21, 2026. 66 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Claude Sonnet 5.5 Replace GPT-5.4
Claude Sonnet 5.5Anthropic
Coding
88.9
Overall
56.0
Output $/M
$10.00
55
GPT-5.4OpenAI
Coding
37.7
Overall
39.0
Output $/M
$15.00
11
vs boards won of 66 shared

Decision reading

Pick Claude Sonnet 5.5 for coding: it scores 88.9 on the Vibe Coding Index against 37.7 for GPT-5.4.

Pick GPT-5.4 when the context window is larger, 1.05M against 1M tokens, or when what matters is LMArena Vision: homework or LMArena Text: legal and government, where it leads.

Model AClaude Sonnet 5.5Anthropic88.9/1002 independent benchmarksNo cost per solved taskModel BGPT-5.4OpenAI37.7/1001 independent benchmark$1.02 per solved task
Shared results
66
Claude Sonnet 5.5 only
29
GPT-5.4 only
43
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
Claude Sonnet 5.5 88.9 from 2 benchmarks, GPT-5.4 37.7 from 1 benchmark.
Widest category
Web design, 27.6 points apart on average over 6 shared benchmarks.
Widest single gap
Design Arena: 3D: Claude Sonnet 5.5 1458 against GPT-5.4 1065, 49.1 points apart on a 0 to 100 scale.
Output price
Claude Sonnet 5.5 $10.00 against GPT-5.4 $15.00 per million output tokens, 1.5x apart.
Context window
Claude Sonnet 5.5 takes 1M tokens, GPT-5.4 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
CategoryClaude Sonnet 5.5BarsGPT-5.4Ties
Coding100
Intelligence20
Agentic work40
Reasoning81
Math60
Knowledge42
Web design60
General158
All shared boards5511
CodingLike-for-likeFour of these boards feed the Vibe Coding Index100
Coding benchmarks for Claude Sonnet 5.5 and GPT-5.4
BenchmarkClaude Sonnet 5.5GPT-5.4Leader
LiveBench coding94.7%Not measuredOnly Claude Sonnet 5.5 measured
LMArena WebDev17681464Claude Sonnet 5.5
AA Coding IndexNot measured71.1Only GPT-5.4 measured
LiveCodeBench (Vals AI)Not measured84.1%Only GPT-5.4 measured
SWE-bench Verified (Vals AI)Not measured78.2%Only GPT-5.4 measured
Terminal-Bench 4 (Vals AI)64.1%Not measuredOnly Claude Sonnet 5.5 measured
Vibe Code Bench (Vals AI)92.4%67.4%Claude Sonnet 5.5
Code migration (Vals AI)69.8%35.0%Claude Sonnet 5.5
ProgramBench (Vals AI)6.5%0.5%Claude Sonnet 5.5
IOI (Vals AI)83.1%Not measuredOnly Claude Sonnet 5.5 measured
Terminal-Bench 2.1 (Vals AI)83.2%Not measuredOnly Claude Sonnet 5.5 measured
SWE-bench Multimodal (Vals AI)58.3%Not measuredOnly Claude Sonnet 5.5 measured
SkillsBench (Vals AI)Not measured51.7%Only GPT-5.4 measured
CyberBench (Vals AI)59.6%Not measuredOnly Claude Sonnet 5.5 measured
SciCode61.0%Not measuredOnly Claude Sonnet 5.5 measured
Terminal-Bench Hard (Artificial Analysis run)Not measured57.6%Only GPT-5.4 measured
Terminal-BenchNot measured81.8%Only GPT-5.4 measured
FrontierCode52.1%Not measuredOnly Claude Sonnet 5.5 measured
FrontierSWE61.9%Not measuredOnly Claude Sonnet 5.5 measured
GSO-BenchNot measured31.4%Only GPT-5.4 measured
WeirdMLNot measured77.7%Only GPT-5.4 measured
MirrorCodeNot measured15.6%Only GPT-5.4 measured
ALE-Bench1819.11607.0Claude Sonnet 5.5
LMArena Text: coding15131496Claude Sonnet 5.5
LMArena Text: software and IT15041491Claude Sonnet 5.5
LMArena WebDev: React18171454Claude Sonnet 5.5
LMArena WebDev: HTML17411478Claude Sonnet 5.5
LMArena WebDev: from an image17371436Claude Sonnet 5.5
Neither model has a result on the other 10 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Sonnet 5.5 and GPT-5.4
BenchmarkClaude Sonnet 5.5GPT-5.4Leader
AA Intelligence Index56.039.0Claude Sonnet 5.5
Epoch Capabilities Index166.2157.3Claude Sonnet 5.5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index40
Agentic work benchmarks for Claude Sonnet 5.5 and GPT-5.4
BenchmarkClaude Sonnet 5.5GPT-5.4Leader
Design Arena: agents building web apps13031059Claude Sonnet 5.5
Design Arena: agents building full-stack appsNot measured1017Only GPT-5.4 measured
Design Arena: agents building mobile apps12651087Claude Sonnet 5.5
Design Arena: agents building Android appsNot measured1037Only GPT-5.4 measured
Design Arena: agents building Godot gamesNot measured1135Only GPT-5.4 measured
Design Arena: spreadsheets1245Not measuredOnly Claude Sonnet 5.5 measured
LiveBench research83.6%Not measuredOnly Claude Sonnet 5.5 measured
LiveBench browser84.0%Not measuredOnly Claude Sonnet 5.5 measured
LiveBench long agentic78.8%Not measuredOnly Claude Sonnet 5.5 measured
SREBench (Vals AI)30.1%Not measuredOnly Claude Sonnet 5.5 measured
Finance Agent (Vals AI)58.1%Not measuredOnly Claude Sonnet 5.5 measured
Tax Agent Bench (Vals AI)42.0%Not measuredOnly Claude Sonnet 5.5 measured
Legal Research Bench (Vals AI)48.1%Not measuredOnly Claude Sonnet 5.5 measured
Harvey's Legal Agent Benchmark (Vals AI)10.4%Not measuredOnly Claude Sonnet 5.5 measured
Excel Modeling Benchmark (Vals AI)75.7%Not measuredOnly Claude Sonnet 5.5 measured
BioMysteryBench (Vals AI)81.1%Not measuredOnly Claude Sonnet 5.5 measured
Terminal-Bench-Science (Vals AI)47.1%Not measuredOnly Claude Sonnet 5.5 measured
Vals Science Index59.1%Not measuredOnly Claude Sonnet 5.5 measured
τ²-Bench TelecomNot measured87.1%Only GPT-5.4 measured
APEX-Agents75.5%52.4%Claude Sonnet 5.5
METR time horizonsNot measured74.3%Only GPT-5.4 measured
DeepResearch BenchNot measured35.1%Only GPT-5.4 measured
PostTrainBenchNot measured19.0%Only GPT-5.4 measured
SpireClimb1.3%Not measuredOnly Claude Sonnet 5.5 measured
Vending-Bench 2$11,165$6,144Claude Sonnet 5.5
Neither model has a result on the other 14 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index81
Reasoning benchmarks for Claude Sonnet 5.5 and GPT-5.4
BenchmarkClaude Sonnet 5.5GPT-5.4Leader
GPQA DiamondNot measured91.7%Only GPT-5.4 measured
LiveBench reasoning91.6%Not measuredOnly Claude Sonnet 5.5 measured
MysteryMechanism (Vals AI)49.1%Not measuredOnly Claude Sonnet 5.5 measured
MMMU Pro (Vals AI)Not measured87.5%Only GPT-5.4 measured
GPQA Diamond (Artificial Analysis run)Not measured92.0%Only GPT-5.4 measured
Humanity's Last Exam (Artificial Analysis run)55.0%43.7%Claude Sonnet 5.5
GPQA Diamond (Epoch AI run)95.6%93.3%Claude Sonnet 5.5
ARC-AGINot measured93.7%Only GPT-5.4 measured
ARC-AGI-2Not measured74.0%Only GPT-5.4 measured
Chess puzzles59.0%48.0%Claude Sonnet 5.5
Mystery game puzzles65.0%37.0%Claude Sonnet 5.5
EBR-benchNot measured25.4%Only GPT-5.4 measured
LMArena Text: hard prompts14941485Claude Sonnet 5.5
LMArena Text: expert15311507Claude Sonnet 5.5
LMArena Text: hard prompts in English15021479Claude Sonnet 5.5
LMArena Vision: diagrams13291327Claude Sonnet 5.5
LMArena Vision: homework13311336GPT-5.4
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index60
Math benchmarks for Claude Sonnet 5.5 and GPT-5.4
BenchmarkClaude Sonnet 5.5GPT-5.4Leader
AIMENot measured96.7%Only GPT-5.4 measured
OTIS Mock AIME100.0%97.8%Claude Sonnet 5.5
FrontierMath, tiers 1 to 388.8%78.6%Claude Sonnet 5.5
FrontierMath, tier 480.5%49.0%Claude Sonnet 5.5
ProofBench100.0%56.0%Claude Sonnet 5.5
LMArena Text: math14971488Claude Sonnet 5.5
LMArena Text: mathematical work15101497Claude Sonnet 5.5
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index42
Knowledge benchmarks for Claude Sonnet 5.5 and GPT-5.4
BenchmarkClaude Sonnet 5.5GPT-5.4Leader
MMLU ProNot measured87.5%Only GPT-5.4 measured
LegalBench (Vals AI)Not measured86.0%Only GPT-5.4 measured
CaseLaw (Vals AI)Not measured63.8%Only GPT-5.4 measured
CorpFin (Vals AI)Not measured65.3%Only GPT-5.4 measured
TaxEval (Vals AI)Not measured74.0%Only GPT-5.4 measured
MortgageTax (Vals AI)Not measured68.3%Only GPT-5.4 measured
MedQA (Vals AI)Not measured96.1%Only GPT-5.4 measured
MedCode (Vals AI)52.9%41.3%Claude Sonnet 5.5
SimpleQA Verified46.5%45.1%Claude Sonnet 5.5
LMArena Text: science14831479Claude Sonnet 5.5
LMArena Text: medicine and healthcare14641458Claude Sonnet 5.5
LMArena Text: legal and government14831486GPT-5.4
LMArena Text: business and finance14681474GPT-5.4
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index60
Web design benchmarks for Claude Sonnet 5.5 and GPT-5.4
BenchmarkClaude Sonnet 5.5GPT-5.4Leader
Design Arena: websites13261199Claude Sonnet 5.5
Design Arena: UI components13671215Claude Sonnet 5.5
Design Arena: game dev14691195Claude Sonnet 5.5
Design Arena: data viz13891196Claude Sonnet 5.5
Design Arena: 3D14581065Claude Sonnet 5.5
Design Arena: all code categories13641180Claude Sonnet 5.5
Design Arena: SVGNot measured1141Only GPT-5.4 measured
Design Arena: ASCII artNot measured1188Only GPT-5.4 measured
LiveBench design85.0%Not measuredOnly Claude Sonnet 5.5 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index158
General benchmarks for Claude Sonnet 5.5 and GPT-5.4
BenchmarkClaude Sonnet 5.5GPT-5.4Leader
Vals Index70.8%Not measuredOnly Claude Sonnet 5.5 measured
LiveBench data analysis59.5%Not measuredOnly Claude Sonnet 5.5 measured
Public Benefits Bench (Vals AI)67.2%Not measuredOnly Claude Sonnet 5.5 measured
SAGE (Vals AI)51.8%43.3%Claude Sonnet 5.5
MedScribe (Vals AI)91.1%77.5%Claude Sonnet 5.5
IFBenchNot measured73.9%Only GPT-5.4 measured
Long context reasoning (AA-LCR)82.7%82.0%Claude Sonnet 5.5
DTBench97.3%94.4%Claude Sonnet 5.5
LMCA68.3%52.0%Claude Sonnet 5.5
CL-benchNot measured27.9%Only GPT-5.4 measured
Furniture assembly75.0%37.5%Claude Sonnet 5.5
CL-bench LifeNot measured21.7%Only GPT-5.4 measured
LMArena Text14731469Claude Sonnet 5.5
LMArena Text: instruction following14921469Claude Sonnet 5.5
LMArena Text: creative writing14671439Claude Sonnet 5.5
LMArena Vision12871303GPT-5.4
LMArena Text: English14841467Claude Sonnet 5.5
LMArena Text: non-English14561465GPT-5.4
LMArena Text: Chinese15351520Claude Sonnet 5.5
LMArena Text: GermanNot measured1472Only GPT-5.4 measured
LMArena Text: JapaneseNot measured1485Only GPT-5.4 measured
LMArena Text: KoreanNot measured1449Only GPT-5.4 measured
LMArena Text: French14991493Claude Sonnet 5.5
LMArena Text: Spanish14511452GPT-5.4
LMArena Text: Russian14541480GPT-5.4
LMArena Text: PolishNot measured1472Only GPT-5.4 measured
LMArena Text: multi-turn14651482GPT-5.4
LMArena Text: longer queries14951473Claude Sonnet 5.5
LMArena Text: writing and language14741458Claude Sonnet 5.5
LMArena Text: entertainment and media14611438Claude Sonnet 5.5
LMArena Vision: English12891301GPT-5.4
LMArena Vision: ChineseNot measured1354Only GPT-5.4 measured
LMArena Vision: reading text12971312GPT-5.4
LMArena Vision: humorNot measured1284Only GPT-5.4 measured
LMArena Vision: recognizing thingsNot measured1251Only GPT-5.4 measured
LMArena Vision: creative writing12421283GPT-5.4
LMArena DocumentNot measured1471Only GPT-5.4 measured
Neither model has a result on the other 9 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Sonnet 5.5 and GPT-5.4
BenchmarkClaude Sonnet 5.5GPT-5.4Leader
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

Claude Sonnet 5.5$0.0070Fits in one request
GPT-5.4$0.010Fits in one request

Claude Sonnet 5.5 costs less

Repository review

50K input + 3K output tokens

Claude Sonnet 5.5$0.130Fits in one request
GPT-5.4$0.170Fits in one request

Claude Sonnet 5.5 costs less

Agent loop

200K input + 10K output tokens

Claude Sonnet 5.5$0.500Fits in one request
GPT-5.4$0.650Fits in one request

Claude Sonnet 5.5 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 Claude Sonnet 5.5 and GPT-5.4
SpecificationAnthropic Claude Sonnet 5.5OpenAI GPT-5.4
MakerAnthropicOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedSeptember 28, 2026March 5, 2026
Context window1M1.05M
Input $/Mtok$2.00$2.50
Output $/Mtok$10.00$15.00
Coding index88.937.7
Independent measurements behind it21
Cost per solved taskNot computable$1.02
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Sonnet 5.5 better than GPT-5.4 for coding?

Pick Claude Sonnet 5.5 for coding: it scores 88.9 on the Vibe Coding Index against 37.7 for GPT-5.4. Pick GPT-5.4 when the context window is larger, 1.05M against 1M tokens, or when what matters is LMArena Vision: homework or LMArena Text: legal and government, where it leads.

Which is cheaper, Claude Sonnet 5.5 or GPT-5.4?

Claude Sonnet 5.5 costs $2.00 per million input tokens and $10.00 per million output tokens; GPT-5.4 costs $2.50 and $15.00. Cost per solved task is known for GPT-5.4 only.

Which has the bigger context window, Claude Sonnet 5.5 or GPT-5.4?

GPT-5.4, with 1.05M tokens against 1M.

How many benchmarks is the Claude Sonnet 5.5 vs GPT-5.4 comparison based on?

66 benchmarks have a result for both models as of October 21, 2026. Claude Sonnet 5.5's coding index rests on 2 independent benchmarks and GPT-5.4's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next