Enter opens the highlighted result. Esc closes.

Claude Haiku 4.5 vs GPT-5

Updated October 21, 2026. 72 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Claude Haiku 4.5 Replace GPT-5
Claude Haiku 4.5Anthropic
Coding
49.8
Overall
16.9
Output $/M
$5.00
17
GPT-5OpenAI
Coding
72.2
Overall
23.0
Output $/M
$10.00
55
vs boards won of 72 shared

Decision reading

Pick GPT-5 for coding: it scores 72.2 on the Vibe Coding Index against 49.8 for Claude Haiku 4.5.

Pick Claude Haiku 4.5 when output tokens cost 2.0x less, or when what matters is AA Coding Index or LMArena Text: coding, where it leads.

Model AClaude Haiku 4.5Anthropic49.8/1003 independent benchmarks$0.56 per solved taskModel BGPT-5OpenAI72.2/1003 independent benchmarks$0.39 per solved task
Shared results
72
Claude Haiku 4.5 only
22
GPT-5 only
37
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 Haiku 4.5 49.8 from 3 benchmarks, GPT-5 72.2 from 3 benchmarks.
Widest category
Reasoning, 13.7 points apart on average over 9 shared benchmarks.
Widest single gap
LiveCodeBench (Vals AI): Claude Haiku 4.5 41.2% against GPT-5 85.9%, 44.7 points apart on a 0 to 100 scale.
Output price
Claude Haiku 4.5 $5.00 against GPT-5 $10.00 per million output tokens, 2.0x apart.
Context window
Claude Haiku 4.5 takes 200K tokens, GPT-5 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-5Ties
Coding38
Intelligence02
Agentic work02
Reasoning36
Math15
Knowledge112
Web design17
General813
All shared boards1755
CodingLike-for-likeFour of these boards feed the Vibe Coding Index38
Coding benchmarks for Claude Haiku 4.5 and GPT-5
BenchmarkClaude Haiku 4.5GPT-5Leader
Aider polyglotNot measured88.0%Only GPT-5 measured
SWE-bench Verified66.6%74.4%GPT-5
SWE-bench Multilingual64.7%Not measuredOnly Claude Haiku 4.5 measured
LiveBench coding48.1%Not measuredOnly Claude Haiku 4.5 measured
LMArena WebDev13301418GPT-5
AA Coding Index43.937.8Claude Haiku 4.5
LiveCodeBench (Vals AI)41.2%85.9%GPT-5
SWE-bench Verified (Vals AI)66.6%69.0%GPT-5
Vibe Code Bench (Vals AI)11.4%20.1%GPT-5
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 measured84.6%Only GPT-5 measured
Terminal-Bench Hard (Artificial Analysis run)Not measured37.9%Only GPT-5 measured
Terminal-Bench35.5%49.6%GPT-5
GSO-BenchNot measured6.9%Only GPT-5 measured
WeirdML45.4%60.7%GPT-5
ALE-BenchNot measured807.6Only GPT-5 measured
LMArena Text: coding14541436Claude Haiku 4.5
LMArena Text: software and IT14391420Claude Haiku 4.5
LMArena WebDev: React1326Not measuredOnly Claude Haiku 4.5 measured
LMArena WebDev: HTML13181427GPT-5
Neither model has a result on the other 16 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Claude Haiku 4.5 and GPT-5
BenchmarkClaude Haiku 4.5GPT-5Leader
AA Intelligence Index16.923.0GPT-5
Epoch Capabilities Index142.2150.0GPT-5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index02
Agentic work benchmarks for Claude Haiku 4.5 and GPT-5
BenchmarkClaude Haiku 4.5GPT-5Leader
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 measured86.5%Only GPT-5 measured
METR time horizonsNot measured69.6%Only GPT-5 measured
Remote Labor IndexNot measured1.7%Only GPT-5 measured
GDPvalNot measured34.8%Only GPT-5 measured
BALROG31.2%32.8%GPT-5
DeepResearch Bench45.5%49.6%GPT-5
Vending-Bench 2$459Not measuredOnly Claude Haiku 4.5 measured
Neither model has a result on the other 24 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index36
Reasoning benchmarks for Claude Haiku 4.5 and GPT-5
BenchmarkClaude Haiku 4.5GPT-5Leader
GPQA Diamond72.2%85.6%GPT-5
LiveBench reasoning61.7%Not measuredOnly Claude Haiku 4.5 measured
MMMU Pro (Vals AI)46.1%81.5%GPT-5
GPQA Diamond (Artificial Analysis run)Not measured85.4%Only GPT-5 measured
Humanity's Last Exam (Artificial Analysis run)Not measured28.5%Only GPT-5 measured
GPQA Diamond (Epoch AI run)71.2%86.2%GPT-5
ARC-AGI47.7%65.7%GPT-5
ARC-AGI-24.0%9.9%GPT-5
SimpleBenchNot measured56.7%Only GPT-5 measured
Chess puzzles8.0%36.0%GPT-5
Mystery game puzzlesNot measured23.0%Only GPT-5 measured
EBR-benchNot measured12.7%Only GPT-5 measured
VPCTNot measured66.0%Only GPT-5 measured
LMArena Text: hard prompts14211415Claude Haiku 4.5
LMArena Text: expert14431419Claude Haiku 4.5
LMArena Text: hard prompts in English14351419Claude Haiku 4.5
LMArena Vision: diagramsNot measured1252Only GPT-5 measured
LMArena Vision: homeworkNot measured1278Only GPT-5 measured
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 Claude Haiku 4.5 and GPT-5
BenchmarkClaude Haiku 4.5GPT-5Leader
AIME82.7%93.4%GPT-5
MATH 500 (Vals AI)Not measured96.0%Only GPT-5 measured
MGSM (Vals AI)92.2%92.8%GPT-5
AA Math IndexNot measured94.3Only GPT-5 measured
AIME 2025 (Artificial Analysis run)Not measured94.3%Only GPT-5 measured
OTIS Mock AIME66.7%91.4%GPT-5
FrontierMath, tiers 1 to 3Not measured55.4%Only GPT-5 measured
FrontierMath, tier 4Not measured22.0%Only GPT-5 measured
ProofBenchNot measured18.0%Only GPT-5 measured
MATH level 596.4%98.1%GPT-5
LMArena Text: math13981407GPT-5
LMArena Text: mathematical work14301405Claude Haiku 4.5
Neither model has a result on the other 1 board here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index112
Knowledge benchmarks for Claude Haiku 4.5 and GPT-5
BenchmarkClaude Haiku 4.5GPT-5Leader
MMLU Pro78.7%86.5%GPT-5
LegalBench (Vals AI)81.2%86.0%GPT-5
CaseLaw (Vals AI)56.5%66.5%GPT-5
CorpFin (Vals AI)60.6%61.1%GPT-5
TaxEval (Vals AI)67.5%73.4%GPT-5
MortgageTax (Vals AI)62.2%65.5%GPT-5
MedQA (Vals AI)79.6%96.3%GPT-5
MedCode (Vals AI)32.7%49.6%GPT-5
MMLU Pro (Artificial Analysis run)Not measured87.1%Only GPT-5 measured
SimpleQA Verified13.2%50.1%GPT-5
GeoBenchNot measured81.0%Only GPT-5 measured
LMArena Text: science14061416GPT-5
LMArena Text: medicine and healthcare13941413GPT-5
LMArena Text: legal and government14001431GPT-5
LMArena Text: business and finance14001400Claude Haiku 4.5
Neither model has a result on the other 2 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index17
Web design benchmarks for Claude Haiku 4.5 and GPT-5
BenchmarkClaude Haiku 4.5GPT-5Leader
Design Arena: websites11221185GPT-5
Design Arena: UI components11001179GPT-5
Design Arena: game dev10971185GPT-5
Design Arena: data viz11241221GPT-5
Design Arena: 3D10721056Claude Haiku 4.5
Design Arena: all code categories11151168GPT-5
Design Arena: SVG10251188GPT-5
Design Arena: ASCII art11391140GPT-5
LiveBench design59.9%Not measuredOnly Claude Haiku 4.5 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index813
General benchmarks for Claude Haiku 4.5 and GPT-5
BenchmarkClaude Haiku 4.5GPT-5Leader
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%43.7%GPT-5
MedScribe (Vals AI)85.2%83.7%Claude Haiku 4.5
Vals Multimodal Index42.9%Not measuredOnly Claude Haiku 4.5 measured
IFBenchNot measured73.1%Only GPT-5 measured
Long context reasoning (AA-LCR)Not measured78.2%Only GPT-5 measured
DTBench73.6%90.7%GPT-5
LMCA30.9%40.0%GPT-5
Fiction.LiveBenchNot measured97.2%Only GPT-5 measured
Creative writing (Lech Mazur)Not measured86.0%Only GPT-5 measured
ExploitBench13.7%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text13971406GPT-5
LMArena Text: instruction following14141388Claude Haiku 4.5
LMArena Text: creative writing13711365Claude Haiku 4.5
LMArena VisionNot measured1232Only GPT-5 measured
LMArena Text: English14141409Claude Haiku 4.5
LMArena Text: non-English13771397GPT-5
LMArena Text: Chinese14181422GPT-5
LMArena Text: German13741416GPT-5
LMArena Text: Japanese13381409GPT-5
LMArena Text: Korean13461360GPT-5
LMArena Text: French14111409Claude Haiku 4.5
LMArena Text: Spanish14211399Claude Haiku 4.5
LMArena Text: Russian13811407GPT-5
LMArena Text: Polish13431431GPT-5
LMArena Text: multi-turn14091426GPT-5
LMArena Text: longer queries14271399Claude Haiku 4.5
LMArena Text: writing and language13861384Claude Haiku 4.5
LMArena Text: entertainment and media13691379GPT-5
LMArena Vision: EnglishNot measured1231Only GPT-5 measured
LMArena Vision: ChineseNot measured1267Only GPT-5 measured
LMArena Vision: reading textNot measured1246Only GPT-5 measured
LMArena Vision: humorNot measured1219Only GPT-5 measured
LMArena Vision: captioningNot measured1212Only GPT-5 measured
LMArena Vision: recognizing thingsNot measured1263Only GPT-5 measured
LMArena Vision: creative writingNot measured1210Only GPT-5 measured
LMArena Document1420Not measuredOnly Claude Haiku 4.5 measured
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
BenchmarkClaude Haiku 4.5GPT-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

Claude Haiku 4.5$0.0035Fits in one request
GPT-5$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$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$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
SpecificationAnthropic Claude Haiku 4.5OpenAI GPT-5
MakerAnthropicOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedOctober 15, 2025August 7, 2025
Context window200K400K
Input $/Mtok$1.00$1.25
Output $/Mtok$5.00$10.00
Coding index49.872.2
Independent measurements behind it33
Cost per solved task$0.56$0.39
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Haiku 4.5 better than GPT-5 for coding?

Pick GPT-5 for coding: it scores 72.2 on the Vibe Coding Index against 49.8 for Claude Haiku 4.5. Pick Claude Haiku 4.5 when output tokens cost 2.0x less, or when what matters is AA Coding Index or LMArena Text: coding, where it leads.

Which is cheaper, Claude Haiku 4.5 or GPT-5?

Claude Haiku 4.5 costs $1.00 per million input tokens and $5.00 per million output tokens; GPT-5 costs $1.25 and $10.00. Per solved SWE-bench Verified task, Claude Haiku 4.5 costs $0.56 and GPT-5 $0.39.

Which has the bigger context window, Claude Haiku 4.5 or GPT-5?

GPT-5, with 400K tokens against 200K.

How many benchmarks is the Claude Haiku 4.5 vs GPT-5 comparison based on?

72 benchmarks have a result for both models as of October 21, 2026. Claude Haiku 4.5's coding index rests on 3 independent benchmarks and GPT-5'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" title="Claude Haiku 4.5 vs GPT-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/claude-haiku-4-5-vs-gpt-5">LLMBenchmark.ai, Claude Haiku 4.5 vs GPT-5</a></p>