Enter opens the highlighted result. Esc closes.

Claude Haiku 4.5 vs GPT-5.4 Nano

GPT-5.4 Nano leads Claude Haiku 4.5 on coding, 44.8 to 35.6 on the Vibe Coding Index, and GPT-5.4 Nano costs 4.0x less per output token ($1.25 vs $5.00 per million). Updated October 22, 2026; 63 benchmarks have a result for both.

Replace Claude Haiku 4.5 Replace GPT-5.4 Nano
Claude Haiku 4.5Anthropic
Coding
35.6
Overall
41.0
Output $/M
$5.00
35
GPT-5.4 NanoOpenAI
Coding
44.8
Overall
45.7
Output $/M
$1.25
28
vs boards won of 63 shared

Claude Haiku 4.5 or GPT-5.4 Nano: which to pick

Pick GPT-5.4 Nano for coding: it scores 44.8 on the Vibe Coding Index against 35.6 for Claude Haiku 4.5, though on 2 benchmarks against 4.

Pick Claude Haiku 4.5 for work measured by Terminal-Bench 2.1 (Vals AI) or LMArena Text: coding, where it leads.

Model AClaude Haiku 4.5Anthropic35.6/1004 independent benchmarks$0.56 per solved taskModel BGPT-5.4 NanoOpenAI44.8/1002 independent benchmarks$0.14 per solved task
Shared results
63
Claude Haiku 4.5 only
35
GPT-5.4 Nano only
22
Like-for-like categories
7 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
Claude Haiku 4.5 35.6 from 4 benchmarks, GPT-5.4 Nano 44.8 from 2 benchmarks.
Widest category
Reasoning, 11.7 points apart on average over 9 shared benchmarks.
Widest single gap
LiveCodeBench (Vals AI): Claude Haiku 4.5 41.2% against GPT-5.4 Nano 84.0%, 42.8 points apart on a 0 to 100 scale.
Output price
Claude Haiku 4.5 $5.00 against GPT-5.4 Nano $1.25 per million output tokens, 4.0x apart.
Context window
Claude Haiku 4.5 takes 200K tokens, GPT-5.4 Nano 400K.

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 Haiku 4.5BarsGPT-5.4 NanoTies
Coding36
Intelligence02
Agentic work23
Reasoning36
Math13
Knowledge102
General166
All shared boards3528
CodingLike-for-likeSix of these boards feed the Vibe Coding Index36
Coding benchmarks for Claude Haiku 4.5 and GPT-5.4 Nano
BenchmarkClaude Haiku 4.5GPT-5.4 NanoLeader
SWE-bench Verified66.6%Not measuredOnly Claude Haiku 4.5 measured
SWE-bench Multilingual64.7%Not measuredOnly Claude Haiku 4.5 measured
LiveBench coding48.1%Not measuredOnly Claude Haiku 4.5 measured
LMArena WebDev1330Not measuredOnly Claude Haiku 4.5 measured
AA Coding Index43.956.1GPT-5.4 Nano
LiveCodeBench (Vals AI)41.2%84.0%GPT-5.4 Nano
SWE-bench Verified (Vals AI)66.6%69.8%GPT-5.4 Nano
Vibe Code Bench (Vals AI)11.4%26.1%GPT-5.4 Nano
Code migration (Vals AI)7.5%14.5%GPT-5.4 Nano
ProgramBench (Vals AI)0.0%Not measuredOnly Claude Haiku 4.5 measured
Terminal-Bench 2.1 (Vals AI)43.8%41.6%Claude Haiku 4.5
SciCodeNot measured47.2%Only GPT-5.4 Nano measured
Terminal-Bench Hard (Artificial Analysis run)Not measured42.4%Only GPT-5.4 Nano measured
Terminal-Bench35.5%Not measuredOnly Claude Haiku 4.5 measured
WeirdML45.4%49.2%GPT-5.4 Nano
ALE-BenchNot measured1004.5Only GPT-5.4 Nano measured
LMArena Text: coding14541404Claude Haiku 4.5
LMArena Text: software and IT14391402Claude Haiku 4.5
LMArena WebDev: React1326Not measuredOnly Claude Haiku 4.5 measured
LMArena WebDev: HTML1318Not measuredOnly Claude Haiku 4.5 measured
Neither model has a result on the other 23 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Claude Haiku 4.5 and GPT-5.4 Nano
BenchmarkClaude Haiku 4.5GPT-5.4 NanoLeader
AA Intelligence Index16.920.7GPT-5.4 Nano
Epoch Capabilities Index142.2146.0GPT-5.4 Nano
Agentic workLike-for-likePublic boards, shown as published, kept out of the index23
Agentic work benchmarks for Claude Haiku 4.5 and GPT-5.4 Nano
BenchmarkClaude Haiku 4.5GPT-5.4 NanoLeader
AA Agentic Index8.016.0GPT-5.4 Nano
LiveBench research42.2%Not measuredOnly Claude Haiku 4.5 measured
LiveBench browser40.0%Not measuredOnly Claude Haiku 4.5 measured
LiveBench long agentic11.1%Not measuredOnly Claude Haiku 4.5 measured
Finance Agent (Vals AI)31.0%38.2%GPT-5.4 Nano
Tax Agent Bench (Vals AI)5.9%5.0%Claude Haiku 4.5
Legal Research Bench (Vals AI)10.6%6.3%Claude Haiku 4.5
Excel Modeling Benchmark (Vals AI)22.7%44.8%GPT-5.4 Nano
τ²-Bench TelecomNot measured76.0%Only GPT-5.4 Nano measured
BALROG31.2%Not measuredOnly Claude Haiku 4.5 measured
DeepResearch Bench45.5%Not measuredOnly Claude Haiku 4.5 measured
Vending-Bench 2$459Not measuredOnly Claude Haiku 4.5 measured
Berkeley Function Calling Leaderboard (BFCL)68.7%Not measuredOnly Claude Haiku 4.5 measured
MCP Atlas40.2%Not measuredOnly Claude Haiku 4.5 measured
Neither model has a result on the other 28 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index36
Reasoning benchmarks for Claude Haiku 4.5 and GPT-5.4 Nano
BenchmarkClaude Haiku 4.5GPT-5.4 NanoLeader
GPQA Diamond72.2%77.5%GPT-5.4 Nano
LiveBench reasoning61.7%Not measuredOnly Claude Haiku 4.5 measured
MMMU Pro (Vals AI)46.1%73.6%GPT-5.4 Nano
GPQA Diamond (Artificial Analysis run)Not measured81.7%Only GPT-5.4 Nano measured
Humanity's Last Exam (Artificial Analysis run)Not measured28.3%Only GPT-5.4 Nano measured
GPQA Diamond (Epoch AI run)71.2%78.5%GPT-5.4 Nano
ARC-AGI47.7%51.5%GPT-5.4 Nano
ARC-AGI-24.0%5.7%GPT-5.4 Nano
Chess puzzles8.0%45.0%GPT-5.4 Nano
Mystery game puzzlesNot measured9.0%Only GPT-5.4 Nano measured
LMArena Text: hard prompts14211381Claude Haiku 4.5
LMArena Text: expert14431396Claude Haiku 4.5
LMArena Text: hard prompts in English14351387Claude Haiku 4.5
LMArena Vision: diagramsNot measured1210Only GPT-5.4 Nano measured
LMArena Vision: homeworkNot measured1225Only GPT-5.4 Nano measured
Kagi LLM BenchmarkNot measured39.7%Only GPT-5.4 Nano measured
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index13
Math benchmarks for Claude Haiku 4.5 and GPT-5.4 Nano
BenchmarkClaude Haiku 4.5GPT-5.4 NanoLeader
AIME82.7%88.8%GPT-5.4 Nano
MGSM (Vals AI)92.2%Not measuredOnly Claude Haiku 4.5 measured
OTIS Mock AIME66.7%87.8%GPT-5.4 Nano
FrontierMath, tiers 1 to 3Not measured44.9%Only GPT-5.4 Nano measured
FrontierMath, tier 4Not measured12.2%Only GPT-5.4 Nano measured
ProofBenchNot measured5.0%Only GPT-5.4 Nano measured
MATH level 596.4%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text: math13981405GPT-5.4 Nano
LMArena Text: mathematical work14301409Claude Haiku 4.5
Neither model has a result on the other 5 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index102
Knowledge benchmarks for Claude Haiku 4.5 and GPT-5.4 Nano
BenchmarkClaude Haiku 4.5GPT-5.4 NanoLeader
MMLU Pro78.7%77.2%Claude Haiku 4.5
LegalBench (Vals AI)81.2%77.9%Claude Haiku 4.5
CaseLaw (Vals AI)56.5%51.9%Claude Haiku 4.5
CorpFin (Vals AI)60.6%61.2%GPT-5.4 Nano
TaxEval (Vals AI)67.5%67.4%Claude Haiku 4.5
MortgageTax (Vals AI)62.2%59.1%Claude Haiku 4.5
MedQA (Vals AI)79.6%Not measuredOnly Claude Haiku 4.5 measured
MedCode (Vals AI)32.7%41.0%GPT-5.4 Nano
SimpleQA Verified13.2%11.7%Claude Haiku 4.5
LMArena Text: science14061374Claude Haiku 4.5
LMArena Text: medicine and healthcare13941369Claude Haiku 4.5
LMArena Text: legal and government14001368Claude Haiku 4.5
LMArena Text: business and finance14001366Claude Haiku 4.5
Neither model has a result on the other 7 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
Web design benchmarks for Claude Haiku 4.5 and GPT-5.4 Nano
BenchmarkClaude Haiku 4.5GPT-5.4 NanoLeader
Design Arena: websites1122Not measuredOnly Claude Haiku 4.5 measured
Design Arena: UI components1097Not measuredOnly Claude Haiku 4.5 measured
Design Arena: game dev1096Not measuredOnly Claude Haiku 4.5 measured
Design Arena: data viz1124Not measuredOnly Claude Haiku 4.5 measured
Design Arena: 3D1071Not measuredOnly Claude Haiku 4.5 measured
Design Arena: all code categories1114Not measuredOnly Claude Haiku 4.5 measured
Design Arena: SVG1025Not measuredOnly Claude Haiku 4.5 measured
Design Arena: ASCII art1140Not measuredOnly Claude Haiku 4.5 measured
LiveBench design59.9%Not measuredOnly Claude Haiku 4.5 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index166
General benchmarks for Claude Haiku 4.5 and GPT-5.4 Nano
BenchmarkClaude Haiku 4.5GPT-5.4 NanoLeader
LiveBench data analysis59.3%Not measuredOnly Claude Haiku 4.5 measured
Public Benefits Bench (Vals AI)54.3%Not measuredOnly Claude Haiku 4.5 measured
SAGE (Vals AI)31.8%38.1%GPT-5.4 Nano
MedScribe (Vals AI)85.2%77.1%Claude Haiku 4.5
Vals Multimodal Index42.9%47.6%GPT-5.4 Nano
IFBenchNot measured75.9%Only GPT-5.4 Nano measured
Long context reasoning (AA-LCR)Not measured76.7%Only GPT-5.4 Nano measured
DTBench73.6%80.3%GPT-5.4 Nano
LMCA30.9%36.9%GPT-5.4 Nano
ExploitBench13.7%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text13971372Claude Haiku 4.5
LMArena Text: instruction following14141362Claude Haiku 4.5
LMArena Text: creative writing13711315Claude Haiku 4.5
LMArena VisionNot measured1196Only GPT-5.4 Nano measured
LMArena Text: English14141381Claude Haiku 4.5
LMArena Text: non-English13771359Claude Haiku 4.5
LMArena Text: Chinese14181391Claude Haiku 4.5
LMArena Text: German13741368Claude Haiku 4.5
LMArena Text: Japanese13381343GPT-5.4 Nano
LMArena Text: Korean13461321Claude Haiku 4.5
LMArena Text: French14111395Claude Haiku 4.5
LMArena Text: Spanish14211371Claude Haiku 4.5
LMArena Text: Russian13811363Claude Haiku 4.5
LMArena Text: Polish13431366GPT-5.4 Nano
LMArena Text: multi-turn14091382Claude Haiku 4.5
LMArena Text: longer queries14271365Claude Haiku 4.5
LMArena Text: writing and language13861338Claude Haiku 4.5
LMArena Text: entertainment and media13691325Claude Haiku 4.5
LMArena Vision: EnglishNot measured1202Only GPT-5.4 Nano measured
LMArena Vision: ChineseNot measured1232Only GPT-5.4 Nano measured
LMArena Vision: reading textNot measured1204Only GPT-5.4 Nano measured
LMArena Vision: humorNot measured1161Only GPT-5.4 Nano measured
LMArena Vision: recognizing thingsNot measured1141Only GPT-5.4 Nano measured
LMArena Vision: creative writingNot measured1159Only GPT-5.4 Nano measured
LMArena Document1420Not measuredOnly Claude Haiku 4.5 measured
MultiChallenge50.5%Not measuredOnly Claude Haiku 4.5 measured
EQ-Bench 41064Not measuredOnly Claude Haiku 4.5 measured
Neither model has a result on the other 11 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Haiku 4.5 and GPT-5.4 Nano
BenchmarkClaude Haiku 4.5GPT-5.4 NanoLeader
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 Haiku 4.5$0.0035Fits in one request
GPT-5.4 Nano$0.0008Fits in one request

GPT-5.4 Nano costs less

Repository review

50K input + 3K output tokens

Claude Haiku 4.5$0.065Fits in one request
GPT-5.4 Nano$0.014Fits in one request

GPT-5.4 Nano costs less

Agent loop

200K input + 10K output tokens

Claude Haiku 4.5$0.250Exceeds the context window
GPT-5.4 Nano$0.052Fits in one request

GPT-5.4 Nano 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 Haiku 4.5 and GPT-5.4 Nano
SpecificationAnthropic Claude Haiku 4.5OpenAI GPT-5.4 Nano
MakerAnthropicOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedOctober 15, 2025March 17, 2026
Context window200K400K
Input $/Mtok$1.00$0.20
Output $/Mtok$5.00$1.25
Coding index35.644.8
Independent measurements behind it42
Cost per solved task$0.56$0.14
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Haiku 4.5 better than GPT-5.4 Nano for coding?

Pick GPT-5.4 Nano for coding: it scores 44.8 on the Vibe Coding Index against 35.6 for Claude Haiku 4.5, though on 2 benchmarks against 4. Pick Claude Haiku 4.5 for work measured by Terminal-Bench 2.1 (Vals AI) or LMArena Text: coding, where it leads.

Which is cheaper, Claude Haiku 4.5 or GPT-5.4 Nano?

Claude Haiku 4.5 costs $1.00 per million input tokens and $5.00 per million output tokens; GPT-5.4 Nano costs $0.20 and $1.25. Per solved SWE-bench Verified task, Claude Haiku 4.5 costs $0.56 and GPT-5.4 Nano $0.14.

Which has the bigger context window, Claude Haiku 4.5 or GPT-5.4 Nano?

GPT-5.4 Nano, with 400K tokens against 200K.

How many benchmarks is the Claude Haiku 4.5 vs GPT-5.4 Nano comparison based on?

63 benchmarks have a result for both models as of October 22, 2026. Claude Haiku 4.5's coding index rests on 4 independent benchmarks and GPT-5.4 Nano'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/claude-haiku-4-5-vs-gpt-5-4-nano" title="Claude Haiku 4.5 vs GPT-5.4 Nano, 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/claude-haiku-4-5-vs-gpt-5-4-nano">LLMBenchmark.ai, Claude Haiku 4.5 vs GPT-5.4 Nano</a></p>