Enter opens the highlighted result. Esc closes.

Claude Haiku 4.5 vs Claude Sonnet 5

Claude Sonnet 5 leads Claude Haiku 4.5 on coding, 57.7 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; 82 benchmarks have a result for both.

Replace Claude Haiku 4.5 Replace Claude Sonnet 5
Claude Haiku 4.5Anthropic
Coding
35.6
Overall
41.0
Output $/M
$5.00
1
Claude Sonnet 5Anthropic
Coding
57.7
Overall
63.2
Output $/M
$10.00
80
vs boards won of 82 shared, 1 tied

Claude Haiku 4.5 or Claude Sonnet 5: which to pick

Pick Claude Sonnet 5 for coding: it scores 57.7 on the Vibe Coding Index against 35.6 for Claude Haiku 4.5.

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 $1.87).

Model AClaude Haiku 4.5Anthropic35.6/1004 independent benchmarks$0.56 per solved taskModel BClaude Sonnet 5Anthropic57.7/1006 independent benchmarks$1.87 per solved task
Shared results
82
Claude Haiku 4.5 only
16
Claude Sonnet 5 only
41
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, Claude Sonnet 5 57.7 from 6 benchmarks.
Widest category
Agentic work, 32.7 points apart on average over 9 shared benchmarks.
Widest single gap
Vibe Code Bench (Vals AI): Claude Haiku 4.5 11.4% against Claude Sonnet 5 81.3%, 69.9 points apart on a 0 to 100 scale.
Output price
Claude Haiku 4.5 $5.00 against Claude Sonnet 5 $10.00 per million output tokens, 2.0x apart.
Context window
Claude Haiku 4.5 takes 200K tokens, Claude Sonnet 5 1M.

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 4.5BarsClaude Sonnet 5Ties
Coding0131 tie
Intelligence02
Agentic work09
Reasoning08
Math03
Knowledge011
Web design09
General125
All shared boards1801 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index013
Coding benchmarks for Claude Haiku 4.5 and Claude Sonnet 5
BenchmarkClaude Haiku 4.5Claude Sonnet 5Leader
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%74.7%Claude Sonnet 5
LMArena WebDev13301540Claude Sonnet 5
AA Coding Index43.971.5Claude Sonnet 5
LiveCodeBench (Vals AI)41.2%82.4%Claude Sonnet 5
SWE-bench Verified (Vals AI)66.6%79.6%Claude Sonnet 5
Terminal-Bench 4 (Vals AI)Not measured10.6%Only Claude Sonnet 5 measured
Vibe Code Bench (Vals AI)11.4%81.3%Claude Sonnet 5
Code migration (Vals AI)7.5%44.4%Claude Sonnet 5
ProgramBench (Vals AI)0.0%0.0%Tie
IOI (Vals AI)Not measured45.0%Only Claude Sonnet 5 measured
Terminal-Bench 2.1 (Vals AI)43.8%74.5%Claude Sonnet 5
Vibe Code Bench 1-100 (Vals AI)Not measured13.8%Only Claude Sonnet 5 measured
SkillsBench (Vals AI)Not measured46.5%Only Claude Sonnet 5 measured
CyberBench (Vals AI)Not measured70.3%Only Claude Sonnet 5 measured
SciCodeNot measured54.3%Only Claude Sonnet 5 measured
Terminal-Bench35.5%Not measuredOnly Claude Haiku 4.5 measured
FrontierCodeNot measured42.7%Only Claude Sonnet 5 measured
GSO-BenchNot measured37.3%Only Claude Sonnet 5 measured
WeirdML45.4%68.8%Claude Sonnet 5
ALE-BenchNot measured1463.1Only Claude Sonnet 5 measured
LMArena Text: coding14541483Claude Sonnet 5
LMArena Text: software and IT14391474Claude Sonnet 5
LMArena WebDev: React13261541Claude Sonnet 5
LMArena WebDev: HTML13181527Claude Sonnet 5
LMArena WebDev: from an imageNot measured1540Only Claude Sonnet 5 measured
SciCodeNot measured10.7%Only Claude Sonnet 5 measured
SWE-Bench Pro V2Not measured93.2%Only Claude Sonnet 5 measured
Neither model has a result on the other 14 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Claude Haiku 4.5 and Claude Sonnet 5
BenchmarkClaude Haiku 4.5Claude Sonnet 5Leader
AA Intelligence Index16.938.2Claude Sonnet 5
Epoch Capabilities Index142.2156.9Claude Sonnet 5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index09
Agentic work benchmarks for Claude Haiku 4.5 and Claude Sonnet 5
BenchmarkClaude Haiku 4.5Claude Sonnet 5Leader
AA Agentic Index8.043.6Claude Sonnet 5
Design Arena: agents building web appsNot measured1245Only Claude Sonnet 5 measured
Design Arena: agents building full-stack appsNot measured1249Only Claude Sonnet 5 measured
Design Arena: agents building mobile appsNot measured1215Only Claude Sonnet 5 measured
Design Arena: agents building Android appsNot measured1226Only Claude Sonnet 5 measured
Design Arena: agents building Godot gamesNot measured1225Only Claude Sonnet 5 measured
Design Arena: agents building gamesNot measured1227Only Claude Sonnet 5 measured
Design Arena: HTML slidesNot measured1157Only Claude Sonnet 5 measured
Design Arena: PowerPoint slidesNot measured1190Only Claude Sonnet 5 measured
Design Arena: spreadsheetsNot measured1079Only Claude Sonnet 5 measured
LiveBench research42.2%82.8%Claude Sonnet 5
LiveBench browser40.0%72.0%Claude Sonnet 5
LiveBench long agentic11.1%39.0%Claude Sonnet 5
SREBench (Vals AI)Not measured0.4%Only Claude Sonnet 5 measured
Finance Agent (Vals AI)31.0%53.9%Claude Sonnet 5
Tax Agent Bench (Vals AI)5.9%29.4%Claude Sonnet 5
Legal Research Bench (Vals AI)10.6%41.8%Claude Sonnet 5
Excel Modeling Benchmark (Vals AI)22.7%66.3%Claude Sonnet 5
Terminal-Bench-Science (Vals AI)Not measured5.7%Only Claude Sonnet 5 measured
APEX-AgentsNot measured54.5%Only Claude Sonnet 5 measured
BALROG31.2%Not measuredOnly Claude Haiku 4.5 measured
DeepResearch Bench45.5%Not measuredOnly Claude Haiku 4.5 measured
Vending-Bench 2$459$6,378Claude Sonnet 5
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 17 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index08
Reasoning benchmarks for Claude Haiku 4.5 and Claude Sonnet 5
BenchmarkClaude Haiku 4.5Claude Sonnet 5Leader
GPQA Diamond72.2%88.9%Claude Sonnet 5
LiveBench reasoning61.7%88.7%Claude Sonnet 5
MMMU Pro (Vals AI)46.1%83.0%Claude Sonnet 5
GPQA Diamond (Artificial Analysis run)Not measured91.1%Only Claude Sonnet 5 measured
Humanity's Last Exam (Artificial Analysis run)Not measured41.3%Only Claude Sonnet 5 measured
GPQA Diamond (Epoch AI run)71.2%90.5%Claude Sonnet 5
ARC-AGI47.7%Not measuredOnly Claude Haiku 4.5 measured
ARC-AGI-24.0%Not measuredOnly Claude Haiku 4.5 measured
SimpleBenchNot measured60.6%Only Claude Sonnet 5 measured
Chess puzzles8.0%45.0%Claude Sonnet 5
Mystery game puzzlesNot measured35.0%Only Claude Sonnet 5 measured
LMArena Text: hard prompts14211461Claude Sonnet 5
LMArena Text: expert14431489Claude Sonnet 5
LMArena Text: hard prompts in English14351464Claude Sonnet 5
LMArena Vision: diagramsNot measured1293Only Claude Sonnet 5 measured
LMArena Vision: homeworkNot measured1311Only Claude Sonnet 5 measured
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index03
Math benchmarks for Claude Haiku 4.5 and Claude Sonnet 5
BenchmarkClaude Haiku 4.5Claude Sonnet 5Leader
AIME82.7%Not measuredOnly Claude Haiku 4.5 measured
MGSM (Vals AI)92.2%Not measuredOnly Claude Haiku 4.5 measured
OTIS Mock AIME66.7%94.7%Claude Sonnet 5
FrontierMath, tiers 1 to 3Not measured65.6%Only Claude Sonnet 5 measured
FrontierMath, tier 4Not measured29.3%Only Claude Sonnet 5 measured
ProofBenchNot measured77.0%Only Claude Sonnet 5 measured
MATH level 596.4%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text: math13981467Claude Sonnet 5
LMArena Text: mathematical work14301481Claude Sonnet 5
Neither model has a result on the other 5 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index011
Knowledge benchmarks for Claude Haiku 4.5 and Claude Sonnet 5
BenchmarkClaude Haiku 4.5Claude Sonnet 5Leader
MMLU Pro78.7%87.5%Claude Sonnet 5
LegalBench (Vals AI)81.2%83.9%Claude Sonnet 5
CaseLaw (Vals AI)56.5%Not measuredOnly Claude Haiku 4.5 measured
CorpFin (Vals AI)60.6%67.0%Claude Sonnet 5
TaxEval (Vals AI)67.5%75.6%Claude Sonnet 5
MortgageTax (Vals AI)62.2%70.0%Claude Sonnet 5
MedQA (Vals AI)79.6%Not measuredOnly Claude Haiku 4.5 measured
MedCode (Vals AI)32.7%47.5%Claude Sonnet 5
SimpleQA Verified13.2%33.7%Claude Sonnet 5
LMArena Text: science14061460Claude Sonnet 5
LMArena Text: medicine and healthcare13941442Claude Sonnet 5
LMArena Text: legal and government14001454Claude Sonnet 5
LMArena Text: business and finance14001436Claude Sonnet 5
Neither model has a result on the other 7 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index09
Web design benchmarks for Claude Haiku 4.5 and Claude Sonnet 5
BenchmarkClaude Haiku 4.5Claude Sonnet 5Leader
Design Arena: websites11221274Claude Sonnet 5
Design Arena: UI components10971277Claude Sonnet 5
Design Arena: game dev10961276Claude Sonnet 5
Design Arena: data viz11241252Claude Sonnet 5
Design Arena: 3D10711261Claude Sonnet 5
Design Arena: all code categories11141275Claude Sonnet 5
Design Arena: SVG10251191Claude Sonnet 5
Design Arena: ASCII art11401206Claude Sonnet 5
LiveBench design59.9%82.0%Claude Sonnet 5
GeneralLike-for-likePublic boards, shown as published, kept out of the index125
General benchmarks for Claude Haiku 4.5 and Claude Sonnet 5
BenchmarkClaude Haiku 4.5Claude Sonnet 5Leader
LiveBench data analysis59.3%71.7%Claude Sonnet 5
Public Benefits Bench (Vals AI)54.3%66.0%Claude Sonnet 5
SAGE (Vals AI)31.8%48.9%Claude Sonnet 5
MedScribe (Vals AI)85.2%76.0%Claude Haiku 4.5
Vals Multimodal Index42.9%68.8%Claude Sonnet 5
Long context reasoning (AA-LCR)Not measured82.0%Only Claude Sonnet 5 measured
DTBench73.6%92.5%Claude Sonnet 5
LMCA30.9%50.0%Claude Sonnet 5
Surface Evolver BenchNot measured60.0%Only Claude Sonnet 5 measured
ExploitBench13.7%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text13971442Claude Sonnet 5
LMArena Text: instruction following14141452Claude Sonnet 5
LMArena Text: creative writing13711416Claude Sonnet 5
LMArena VisionNot measured1273Only Claude Sonnet 5 measured
LMArena Text: English14141450Claude Sonnet 5
LMArena Text: non-English13771431Claude Sonnet 5
LMArena Text: Chinese14181478Claude Sonnet 5
LMArena Text: German13741442Claude Sonnet 5
LMArena Text: Japanese13381422Claude Sonnet 5
LMArena Text: Korean13461412Claude Sonnet 5
LMArena Text: French14111463Claude Sonnet 5
LMArena Text: Spanish14211438Claude Sonnet 5
LMArena Text: Russian13811450Claude Sonnet 5
LMArena Text: Polish13431425Claude Sonnet 5
LMArena Text: multi-turn14091453Claude Sonnet 5
LMArena Text: longer queries14271462Claude Sonnet 5
LMArena Text: writing and language13861436Claude Sonnet 5
LMArena Text: entertainment and media13691411Claude Sonnet 5
LMArena Vision: EnglishNot measured1275Only Claude Sonnet 5 measured
LMArena Vision: ChineseNot measured1331Only Claude Sonnet 5 measured
LMArena Vision: reading textNot measured1288Only Claude Sonnet 5 measured
LMArena Vision: humorNot measured1261Only Claude Sonnet 5 measured
LMArena Vision: creative writingNot measured1246Only Claude Sonnet 5 measured
LMArena Document14201466Claude Sonnet 5
MultiChallenge50.5%Not measuredOnly Claude Haiku 4.5 measured
EQ-Bench 410641236Claude Sonnet 5
Neither model has a result on the other 12 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 Claude Sonnet 5
BenchmarkClaude Haiku 4.5Claude Sonnet 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
Claude Sonnet 5$0.0070Fits 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
Claude Sonnet 5$0.130Fits 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
Claude Sonnet 5$0.500Fits 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 Claude Sonnet 5
SpecificationAnthropic Claude Haiku 4.5Anthropic Claude Sonnet 5
MakerAnthropicAnthropic
WeightsNo public weights listedNo public weights listed
ReleasedOctober 15, 2025June 30, 2026
Context window200K1M
Input $/Mtok$1.00$2.00
Output $/Mtok$5.00$10.00
Coding index35.657.7
Independent measurements behind it46
Cost per solved task$0.56$1.87
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Haiku 4.5 better than Claude Sonnet 5 for coding?

Pick Claude Sonnet 5 for coding: it scores 57.7 on the Vibe Coding Index against 35.6 for Claude Haiku 4.5. 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 $1.87).

Which is cheaper, Claude Haiku 4.5 or Claude Sonnet 5?

Claude Haiku 4.5 costs $1.00 per million input tokens and $5.00 per million output tokens; Claude Sonnet 5 costs $2.00 and $10.00. Per solved SWE-bench Verified task, Claude Haiku 4.5 costs $0.56 and Claude Sonnet 5 $1.87.

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

Claude Sonnet 5, with 1M tokens against 200K.

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

82 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 Claude Sonnet 5's on 6. 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-claude-sonnet-5" title="Claude Haiku 4.5 vs Claude Sonnet 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-claude-sonnet-5">LLMBenchmark.ai, Claude Haiku 4.5 vs Claude Sonnet 5</a></p>