Enter opens the highlighted result. Esc closes.

Claude Haiku 4.5 vs GPT-5.1

GPT-5.1 leads Claude Haiku 4.5 on coding, 40.4 to 35.6 on the Vibe Coding Index, and Claude Haiku 4.5 costs 2.0x less per output token ($5.00 vs $10.00 per million). Updated October 22, 2026; 73 benchmarks have a result for both.

Replace Claude Haiku 4.5 Replace GPT-5.1
Claude Haiku 4.5Anthropic
Coding
35.6
Overall
41.0
Output $/M
$5.00
8
GPT-5.1OpenAI
Coding
40.4
Overall
55.0
Output $/M
$10.00
65
vs boards won of 73 shared

Claude Haiku 4.5 or GPT-5.1: which to pick

Pick GPT-5.1 for coding: it scores 40.4 on the Vibe Coding Index against 35.6 for Claude Haiku 4.5, though on 3 benchmarks against 4.

Pick Claude Haiku 4.5 for output tokens 2.0x cheaper ($5.00 vs $10.00 per million) and a lower cost per solved task ($0.56 against $1.02).

Model AClaude Haiku 4.5Anthropic35.6/1004 independent benchmarks$0.56 per solved taskModel BGPT-5.1OpenAI40.4/1003 independent benchmarks$1.02 per solved task
Shared results
73
Claude Haiku 4.5 only
22
GPT-5.1 only
28
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
Claude Haiku 4.5 35.6 from 4 benchmarks, GPT-5.1 40.4 from 3 benchmarks.
Widest category
Reasoning, 17.3 points apart on average over 9 shared benchmarks.
Widest single gap
LiveCodeBench (Vals AI): Claude Haiku 4.5 41.2% against GPT-5.1 86.5%, 45.3 points apart on a 0 to 100 scale.
Output price
Claude Haiku 4.5 $5.00 against GPT-5.1 $10.00 per million output tokens, 2.0x apart.
Context window
Claude Haiku 4.5 takes 200K tokens, GPT-5.1 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-5.1Ties
Coding39
Intelligence02
Agentic work11
Reasoning09
Math05
Knowledge112
Web design26
General121
All shared boards865
CodingLike-for-likeSix of these boards feed the Vibe Coding Index39
Coding benchmarks for Claude Haiku 4.5 and GPT-5.1
BenchmarkClaude Haiku 4.5GPT-5.1Leader
SWE-bench Verified66.6%66.0%Claude Haiku 4.5
SWE-bench Multilingual64.7%Not measuredOnly Claude Haiku 4.5 measured
LiveBench coding48.1%Not measuredOnly Claude Haiku 4.5 measured
LMArena WebDev13301396GPT-5.1
AA Coding Index43.949.4GPT-5.1
LiveCodeBench (Vals AI)41.2%86.5%GPT-5.1
SWE-bench Verified (Vals AI)66.6%69.8%GPT-5.1
Vibe Code Bench (Vals AI)11.4%24.6%GPT-5.1
Code migration (Vals AI)7.5%Not measuredOnly Claude Haiku 4.5 measured
ProgramBench (Vals AI)0.0%Not measuredOnly Claude Haiku 4.5 measured
Terminal-Bench 2.1 (Vals AI)43.8%Not measuredOnly Claude Haiku 4.5 measured
LiveCodeBench (Artificial Analysis run)Not measured86.8%Only GPT-5.1 measured
Terminal-Bench Hard (Artificial Analysis run)Not measured45.5%Only GPT-5.1 measured
Terminal-Bench35.5%47.6%GPT-5.1
GSO-BenchNot measured13.7%Only GPT-5.1 measured
WeirdML45.4%60.8%GPT-5.1
LMArena Text: coding14541453Claude Haiku 4.5
LMArena Text: software and IT14391454GPT-5.1
LMArena WebDev: React13261307Claude Haiku 4.5
LMArena WebDev: HTML13181405GPT-5.1
LMArena WebDev: from an imageNot measured1421Only GPT-5.1 measured
Neither model has a result on the other 18 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Claude Haiku 4.5 and GPT-5.1
BenchmarkClaude Haiku 4.5GPT-5.1Leader
AA Intelligence Index16.924.7GPT-5.1
Epoch Capabilities Index142.2149.8GPT-5.1
Agentic workLike-for-likePublic boards, shown as published, kept out of the index11
Agentic work benchmarks for Claude Haiku 4.5 and GPT-5.1
BenchmarkClaude Haiku 4.5GPT-5.1Leader
AA Agentic Index8.0Not measuredOnly Claude Haiku 4.5 measured
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%Not measuredOnly Claude Haiku 4.5 measured
Tax Agent Bench (Vals AI)5.9%Not measuredOnly Claude Haiku 4.5 measured
Legal Research Bench (Vals AI)10.6%Not measuredOnly Claude Haiku 4.5 measured
Excel Modeling Benchmark (Vals AI)22.7%Not measuredOnly Claude Haiku 4.5 measured
τ²-Bench TelecomNot measured81.9%Only GPT-5.1 measured
BALROG31.2%Not measuredOnly Claude Haiku 4.5 measured
DeepResearch Bench45.5%42.8%Claude Haiku 4.5
Vending-Bench 2$459$1,473GPT-5.1
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 index09
Reasoning benchmarks for Claude Haiku 4.5 and GPT-5.1
BenchmarkClaude Haiku 4.5GPT-5.1Leader
GPQA Diamond72.2%86.6%GPT-5.1
LiveBench reasoning61.7%Not measuredOnly Claude Haiku 4.5 measured
MMMU Pro (Vals AI)46.1%83.2%GPT-5.1
GPQA Diamond (Artificial Analysis run)Not measured87.3%Only GPT-5.1 measured
Humanity's Last Exam (Artificial Analysis run)Not measured28.5%Only GPT-5.1 measured
GPQA Diamond (Epoch AI run)71.2%87.6%GPT-5.1
ARC-AGI47.7%72.8%GPT-5.1
ARC-AGI-24.0%17.6%GPT-5.1
SimpleBenchNot measured53.2%Only GPT-5.1 measured
Chess puzzles8.0%42.0%GPT-5.1
Mystery game puzzlesNot measured19.0%Only GPT-5.1 measured
VPCTNot measured58.7%Only GPT-5.1 measured
LMArena Text: hard prompts14211457GPT-5.1
LMArena Text: expert14431470GPT-5.1
LMArena Text: hard prompts in English14351462GPT-5.1
LMArena Vision: diagramsNot measured1264Only GPT-5.1 measured
LMArena Vision: homeworkNot measured1272Only GPT-5.1 measured
Neither model has a result on the other 5 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index05
Math benchmarks for Claude Haiku 4.5 and GPT-5.1
BenchmarkClaude Haiku 4.5GPT-5.1Leader
AIME82.7%93.3%GPT-5.1
MGSM (Vals AI)92.2%93.0%GPT-5.1
AA Math IndexNot measured94.0Only GPT-5.1 measured
AIME 2025 (Artificial Analysis run)Not measured94.0%Only GPT-5.1 measured
OTIS Mock AIME66.7%88.6%GPT-5.1
MATH level 596.4%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text: math13981446GPT-5.1
LMArena Text: mathematical work14301449GPT-5.1
Neither model has a result on the other 5 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index112
Knowledge benchmarks for Claude Haiku 4.5 and GPT-5.1
BenchmarkClaude Haiku 4.5GPT-5.1Leader
MMLU Pro78.7%86.4%GPT-5.1
LegalBench (Vals AI)81.2%85.7%GPT-5.1
CaseLaw (Vals AI)56.5%73.4%GPT-5.1
CorpFin (Vals AI)60.6%63.8%GPT-5.1
TaxEval (Vals AI)67.5%74.9%GPT-5.1
MortgageTax (Vals AI)62.2%61.4%Claude Haiku 4.5
MedQA (Vals AI)79.6%96.4%GPT-5.1
MedCode (Vals AI)32.7%52.7%GPT-5.1
MMLU Pro (Artificial Analysis run)Not measured87.0%Only GPT-5.1 measured
SimpleQA Verified13.2%48.0%GPT-5.1
LMArena Text: science14061459GPT-5.1
LMArena Text: medicine and healthcare13941456GPT-5.1
LMArena Text: legal and government14001459GPT-5.1
LMArena Text: business and finance14001431GPT-5.1
FACTS Benchmark SuiteNot measured45.0%Only GPT-5.1 measured
Neither model has a result on the other 3 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index26
Web design benchmarks for Claude Haiku 4.5 and GPT-5.1
BenchmarkClaude Haiku 4.5GPT-5.1Leader
Design Arena: websites11221187GPT-5.1
Design Arena: UI components10971163GPT-5.1
Design Arena: game dev10971178GPT-5.1
Design Arena: data viz11241204GPT-5.1
Design Arena: 3D10711060Claude Haiku 4.5
Design Arena: all code categories11141170GPT-5.1
Design Arena: SVG10251149GPT-5.1
Design Arena: ASCII art11401119Claude Haiku 4.5
LiveBench design59.9%Not measuredOnly Claude Haiku 4.5 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index121
General benchmarks for Claude Haiku 4.5 and GPT-5.1
BenchmarkClaude Haiku 4.5GPT-5.1Leader
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%43.2%GPT-5.1
MedScribe (Vals AI)85.2%88.1%GPT-5.1
Vals Multimodal Index42.9%Not measuredOnly Claude Haiku 4.5 measured
IFBenchNot measured72.9%Only GPT-5.1 measured
Long context reasoning (AA-LCR)Not measured80.0%Only GPT-5.1 measured
DTBench73.6%90.1%GPT-5.1
LMCA30.9%43.9%GPT-5.1
CL-benchNot measured23.7%Only GPT-5.1 measured
ExploitBench13.7%Not measuredOnly Claude Haiku 4.5 measured
CL-bench LifeNot measured17.3%Only GPT-5.1 measured
LMArena Text13971443GPT-5.1
LMArena Text: instruction following14141443GPT-5.1
LMArena Text: creative writing13711427GPT-5.1
LMArena VisionNot measured1250Only GPT-5.1 measured
LMArena Text: English14141451GPT-5.1
LMArena Text: non-English13771431GPT-5.1
LMArena Text: Chinese14181495GPT-5.1
LMArena Text: German13741438GPT-5.1
LMArena Text: Japanese13381453GPT-5.1
LMArena Text: Korean13461401GPT-5.1
LMArena Text: French14111450GPT-5.1
LMArena Text: Spanish14211433GPT-5.1
LMArena Text: Russian13811435GPT-5.1
LMArena Text: Polish13431440GPT-5.1
LMArena Text: multi-turn14091450GPT-5.1
LMArena Text: longer queries14271448GPT-5.1
LMArena Text: writing and language13861428GPT-5.1
LMArena Text: entertainment and media13691415GPT-5.1
LMArena Vision: EnglishNot measured1252Only GPT-5.1 measured
LMArena Vision: ChineseNot measured1270Only GPT-5.1 measured
LMArena Vision: reading textNot measured1255Only GPT-5.1 measured
LMArena Vision: humorNot measured1263Only GPT-5.1 measured
LMArena Vision: captioningNot measured1252Only GPT-5.1 measured
LMArena Vision: recognizing thingsNot measured1232Only GPT-5.1 measured
LMArena Vision: creative writingNot measured1266Only GPT-5.1 measured
LMArena Document14201403Claude Haiku 4.5
Neither model has a result on the other 8 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-5.1
BenchmarkClaude Haiku 4.5GPT-5.1Leader
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-5.1$0.0063Fits in one request

Claude Haiku 4.5 costs less

Repository review

50K input + 3K output tokens

Claude Haiku 4.5$0.065Fits in one request
GPT-5.1$0.092Fits in one request

Claude Haiku 4.5 costs less

Agent loop

200K input + 10K output tokens

Claude Haiku 4.5$0.250Exceeds the context window
GPT-5.1$0.350Fits in one request

Claude Haiku 4.5 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 Haiku 4.5 and GPT-5.1
SpecificationAnthropic Claude Haiku 4.5OpenAI GPT-5.1
MakerAnthropicOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedOctober 15, 2025November 13, 2025
Context window200K400K
Input $/Mtok$1.00$1.25
Output $/Mtok$5.00$10.00
Coding index35.640.4
Independent measurements behind it43
Cost per solved task$0.56$1.02
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Haiku 4.5 better than GPT-5.1 for coding?

Pick GPT-5.1 for coding: it scores 40.4 on the Vibe Coding Index against 35.6 for Claude Haiku 4.5, though on 3 benchmarks against 4. Pick Claude Haiku 4.5 for output tokens 2.0x cheaper ($5.00 vs $10.00 per million) and a lower cost per solved task ($0.56 against $1.02).

Which is cheaper, Claude Haiku 4.5 or GPT-5.1?

Claude Haiku 4.5 costs $1.00 per million input tokens and $5.00 per million output tokens; GPT-5.1 costs $1.25 and $10.00. Per solved SWE-bench Verified task, Claude Haiku 4.5 costs $0.56 and GPT-5.1 $1.02.

Which has the bigger context window, Claude Haiku 4.5 or GPT-5.1?

GPT-5.1, with 400K tokens against 200K.

How many benchmarks is the Claude Haiku 4.5 vs GPT-5.1 comparison based on?

73 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-5.1's on 3. 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-5-1" title="Claude Haiku 4.5 vs GPT-5.1, 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-5-1">LLMBenchmark.ai, Claude Haiku 4.5 vs GPT-5.1</a></p>