Enter opens the highlighted result. Esc closes.

Claude Haiku 4.5 vs GPT-5.4 Mini

GPT-5.4 Mini leads Claude Haiku 4.5 on coding, 35.8 to 35.6 on the Vibe Coding Index, at about the same output price ($4.50 vs $5.00 per million). Updated October 22, 2026; 65 benchmarks have a result for both.

Replace Claude Haiku 4.5 Replace GPT-5.4 Mini
Claude Haiku 4.5Anthropic
Coding
35.6
Overall
41.0
Output $/M
$5.00
12
GPT-5.4 MiniOpenAI
Coding
35.8
Overall
44.0
Output $/M
$4.50
52
vs boards won of 65 shared, 1 tied

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

Claude Haiku 4.5 and GPT-5.4 Mini are level for coding, 35.6 against 35.8 on the Vibe Coding Index, so price and context decide.

Pick Claude Haiku 4.5 for a lower cost per solved task ($0.56 against $0.70) and work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads. Pick GPT-5.4 Mini for output tokens 1.1x cheaper ($4.50 vs $5.00 per million) and a larger context window (400K against 200K tokens).

Model AClaude Haiku 4.5Anthropic35.6/1004 independent benchmarks$0.56 per solved taskModel BGPT-5.4 MiniOpenAI35.8/1005 independent benchmarks$0.70 per solved task
Shared results
65
Claude Haiku 4.5 only
30
GPT-5.4 Mini only
24
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 Mini 35.8 from 5 benchmarks.
Widest category
Coding, 12.8 points apart on average over 13 shared benchmarks.
Widest single gap
LiveCodeBench (Vals AI): Claude Haiku 4.5 41.2% against GPT-5.4 Mini 81.5%, 40.3 points apart on a 0 to 100 scale.
Output price
Claude Haiku 4.5 $5.00 against GPT-5.4 Mini $4.50 per million output tokens, 1.1x apart.
Context window
Claude Haiku 4.5 takes 200K tokens, GPT-5.4 Mini 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 MiniTies
Coding2101 tie
Intelligence02
Agentic work15
Reasoning27
Math13
Knowledge19
General516
All shared boards12521 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index210
Coding benchmarks for Claude Haiku 4.5 and GPT-5.4 Mini
BenchmarkClaude Haiku 4.5GPT-5.4 MiniLeader
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 WebDev13301397GPT-5.4 Mini
AA Coding Index43.956.1GPT-5.4 Mini
LiveCodeBench (Vals AI)41.2%81.5%GPT-5.4 Mini
SWE-bench Verified (Vals AI)66.6%73.0%GPT-5.4 Mini
Terminal-Bench 4 (Vals AI)Not measured2.5%Only GPT-5.4 Mini measured
Vibe Code Bench (Vals AI)11.4%48.0%GPT-5.4 Mini
Code migration (Vals AI)7.5%12.9%GPT-5.4 Mini
ProgramBench (Vals AI)0.0%0.0%Tie
Terminal-Bench 2.1 (Vals AI)43.8%54.7%GPT-5.4 Mini
SciCodeNot measured52.1%Only GPT-5.4 Mini measured
Terminal-Bench Hard (Artificial Analysis run)Not measured52.3%Only GPT-5.4 Mini measured
Terminal-Bench35.5%Not measuredOnly Claude Haiku 4.5 measured
FrontierCodeNot measured27.0%Only GPT-5.4 Mini measured
WeirdML45.4%60.3%GPT-5.4 Mini
ALE-BenchNot measured1188.6Only GPT-5.4 Mini measured
LMArena Text: coding14541438Claude Haiku 4.5
LMArena Text: software and IT14391436Claude Haiku 4.5
LMArena WebDev: React13261386GPT-5.4 Mini
LMArena WebDev: HTML13181419GPT-5.4 Mini
Neither model has a result on the other 17 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 Mini
BenchmarkClaude Haiku 4.5GPT-5.4 MiniLeader
AA Intelligence Index16.924.1GPT-5.4 Mini
Epoch Capabilities Index142.2148.7GPT-5.4 Mini
Agentic workLike-for-likePublic boards, shown as published, kept out of the index15
Agentic work benchmarks for Claude Haiku 4.5 and GPT-5.4 Mini
BenchmarkClaude Haiku 4.5GPT-5.4 MiniLeader
AA Agentic Index8.017.9GPT-5.4 Mini
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%45.4%GPT-5.4 Mini
Tax Agent Bench (Vals AI)5.9%8.8%GPT-5.4 Mini
Legal Research Bench (Vals AI)10.6%12.5%GPT-5.4 Mini
Excel Modeling Benchmark (Vals AI)22.7%45.4%GPT-5.4 Mini
τ²-Bench TelecomNot measured83.3%Only GPT-5.4 Mini measured
BALROG31.2%Not measuredOnly Claude Haiku 4.5 measured
DeepResearch Bench45.5%36.3%Claude Haiku 4.5
Vending-Bench 2$459Not measuredOnly Claude Haiku 4.5 measured
Berkeley Function Calling Leaderboard (BFCL)68.7%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 index27
Reasoning benchmarks for Claude Haiku 4.5 and GPT-5.4 Mini
BenchmarkClaude Haiku 4.5GPT-5.4 MiniLeader
GPQA Diamond72.2%83.1%GPT-5.4 Mini
LiveBench reasoning61.7%Not measuredOnly Claude Haiku 4.5 measured
MMMU Pro (Vals AI)46.1%79.3%GPT-5.4 Mini
GPQA Diamond (Artificial Analysis run)Not measured87.5%Only GPT-5.4 Mini measured
Humanity's Last Exam (Artificial Analysis run)Not measured28.1%Only GPT-5.4 Mini measured
GPQA Diamond (Epoch AI run)71.2%86.9%GPT-5.4 Mini
ARC-AGI47.7%63.7%GPT-5.4 Mini
ARC-AGI-24.0%18.9%GPT-5.4 Mini
Chess puzzles8.0%23.0%GPT-5.4 Mini
Mystery game puzzlesNot measured11.0%Only GPT-5.4 Mini measured
LMArena Text: hard prompts14211424GPT-5.4 Mini
LMArena Text: expert14431435Claude Haiku 4.5
LMArena Text: hard prompts in English14351420Claude Haiku 4.5
LMArena Vision: diagramsNot measured1266Only GPT-5.4 Mini measured
LMArena Vision: homeworkNot measured1285Only GPT-5.4 Mini measured
Kagi LLM BenchmarkNot measured37.9%Only GPT-5.4 Mini measured
Neither model has a result on the other 6 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 Mini
BenchmarkClaude Haiku 4.5GPT-5.4 MiniLeader
AIME82.7%95.6%GPT-5.4 Mini
MGSM (Vals AI)92.2%Not measuredOnly Claude Haiku 4.5 measured
OTIS Mock AIME66.7%88.9%GPT-5.4 Mini
FrontierMath, tiers 1 to 3Not measured51.2%Only GPT-5.4 Mini measured
FrontierMath, tier 4Not measured9.8%Only GPT-5.4 Mini measured
ProofBenchNot measured21.0%Only GPT-5.4 Mini measured
MATH level 596.4%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text: math13981418GPT-5.4 Mini
LMArena Text: mathematical work14301429Claude Haiku 4.5
Neither model has a result on the other 4 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index19
Knowledge benchmarks for Claude Haiku 4.5 and GPT-5.4 Mini
BenchmarkClaude Haiku 4.5GPT-5.4 MiniLeader
MMLU Pro78.7%84.5%GPT-5.4 Mini
LegalBench (Vals AI)81.2%Not measuredOnly Claude Haiku 4.5 measured
CaseLaw (Vals AI)56.5%51.7%Claude Haiku 4.5
CorpFin (Vals AI)60.6%60.9%GPT-5.4 Mini
TaxEval (Vals AI)67.5%71.2%GPT-5.4 Mini
MortgageTax (Vals AI)62.2%63.5%GPT-5.4 Mini
MedQA (Vals AI)79.6%Not measuredOnly Claude Haiku 4.5 measured
MedCode (Vals AI)32.7%Not measuredOnly Claude Haiku 4.5 measured
SimpleQA Verified13.2%29.4%GPT-5.4 Mini
LMArena Text: science14061417GPT-5.4 Mini
LMArena Text: medicine and healthcare13941395GPT-5.4 Mini
LMArena Text: legal and government14001414GPT-5.4 Mini
LMArena Text: business and finance14001418GPT-5.4 Mini
Neither model has a result on the other 5 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 Mini
BenchmarkClaude Haiku 4.5GPT-5.4 MiniLeader
Design Arena: websites1122Not measuredOnly Claude Haiku 4.5 measured
Design Arena: UI components1097Not measuredOnly Claude Haiku 4.5 measured
Design Arena: game dev1097Not 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 index516
General benchmarks for Claude Haiku 4.5 and GPT-5.4 Mini
BenchmarkClaude Haiku 4.5GPT-5.4 MiniLeader
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%50.8%GPT-5.4 Mini
MedScribe (Vals AI)85.2%Not measuredOnly Claude Haiku 4.5 measured
Vals Multimodal Index42.9%54.2%GPT-5.4 Mini
IFBenchNot measured73.3%Only GPT-5.4 Mini measured
Long context reasoning (AA-LCR)Not measured77.0%Only GPT-5.4 Mini measured
DTBench73.6%80.0%GPT-5.4 Mini
LMCA30.9%40.8%GPT-5.4 Mini
ExploitBench13.7%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text13971412GPT-5.4 Mini
LMArena Text: instruction following14141405Claude Haiku 4.5
LMArena Text: creative writing13711370Claude Haiku 4.5
LMArena VisionNot measured1245Only GPT-5.4 Mini measured
LMArena Text: English14141412Claude Haiku 4.5
LMArena Text: non-English13771405GPT-5.4 Mini
LMArena Text: Chinese14181446GPT-5.4 Mini
LMArena Text: German13741408GPT-5.4 Mini
LMArena Text: Japanese13381375GPT-5.4 Mini
LMArena Text: Korean13461370GPT-5.4 Mini
LMArena Text: French14111441GPT-5.4 Mini
LMArena Text: Spanish14211405Claude Haiku 4.5
LMArena Text: Russian13811417GPT-5.4 Mini
LMArena Text: Polish13431415GPT-5.4 Mini
LMArena Text: multi-turn14091429GPT-5.4 Mini
LMArena Text: longer queries14271408Claude Haiku 4.5
LMArena Text: writing and language13861393GPT-5.4 Mini
LMArena Text: entertainment and media13691373GPT-5.4 Mini
LMArena Vision: EnglishNot measured1244Only GPT-5.4 Mini measured
LMArena Vision: ChineseNot measured1286Only GPT-5.4 Mini measured
LMArena Vision: reading textNot measured1253Only GPT-5.4 Mini measured
LMArena Vision: humorNot measured1235Only GPT-5.4 Mini measured
LMArena Vision: recognizing thingsNot measured1218Only GPT-5.4 Mini measured
LMArena Vision: creative writingNot measured1222Only GPT-5.4 Mini measured
LMArena Document1420Not 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 Mini
BenchmarkClaude Haiku 4.5GPT-5.4 MiniLeader
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 Mini$0.0030Fits in one request

GPT-5.4 Mini costs less

Repository review

50K input + 3K output tokens

Claude Haiku 4.5$0.065Fits in one request
GPT-5.4 Mini$0.051Fits in one request

GPT-5.4 Mini costs less

Agent loop

200K input + 10K output tokens

Claude Haiku 4.5$0.250Exceeds the context window
GPT-5.4 Mini$0.195Fits in one request

GPT-5.4 Mini 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 Mini
SpecificationAnthropic Claude Haiku 4.5OpenAI GPT-5.4 Mini
MakerAnthropicOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedOctober 15, 2025March 17, 2026
Context window200K400K
Input $/Mtok$1.00$0.75
Output $/Mtok$5.00$4.50
Coding index35.635.8
Independent measurements behind it45
Cost per solved task$0.56$0.70
SourceOpenRouter listingOpenRouter listing

Questions

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

Claude Haiku 4.5 and GPT-5.4 Mini are level for coding, 35.6 against 35.8 on the Vibe Coding Index, so price and context decide. Pick Claude Haiku 4.5 for a lower cost per solved task ($0.56 against $0.70) and work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads. Pick GPT-5.4 Mini for output tokens 1.1x cheaper ($4.50 vs $5.00 per million) and a larger context window (400K against 200K tokens).

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

Claude Haiku 4.5 costs $1.00 per million input tokens and $5.00 per million output tokens; GPT-5.4 Mini costs $0.75 and $4.50. Per solved SWE-bench Verified task, Claude Haiku 4.5 costs $0.56 and GPT-5.4 Mini $0.70.

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

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

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

65 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 Mini'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/claude-haiku-4-5-vs-gpt-5-4-mini" title="Claude Haiku 4.5 vs GPT-5.4 Mini, 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-mini">LLMBenchmark.ai, Claude Haiku 4.5 vs GPT-5.4 Mini</a></p>