Enter opens the highlighted result. Esc closes.

Claude Haiku 4.5 vs Claude Sonnet 4.5

Claude Sonnet 4.5 leads Claude Haiku 4.5 on coding, 39.5 to 35.6 on the Vibe Coding Index, and Claude Haiku 4.5 costs 3.0x less per output token ($5.00 vs $15.00 per million). Updated October 22, 2026; 77 benchmarks have a result for both.

Replace Claude Haiku 4.5 Replace Claude Sonnet 4.5
Claude Haiku 4.5Anthropic
Coding
35.6
Overall
41.0
Output $/M
$5.00
1
Claude Sonnet 4.5Anthropic
Coding
39.5
Overall
49.5
Output $/M
$15.00
76
vs boards won of 77 shared

Claude Haiku 4.5 or Claude Sonnet 4.5: which to pick

Pick Claude Sonnet 4.5 for coding: it scores 39.5 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 3.0x cheaper ($5.00 vs $15.00 per million) and a lower cost per solved task ($0.56 against $1.16).

Model AClaude Haiku 4.5Anthropic35.6/1004 independent benchmarks$0.56 per solved taskModel BClaude Sonnet 4.5Anthropic39.5/1003 independent benchmarks$1.16 per solved task
Shared results
77
Claude Haiku 4.5 only
18
Claude Sonnet 4.5 only
18
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 4.5 39.5 from 3 benchmarks.
Widest category
Reasoning, 11.2 points apart on average over 9 shared benchmarks.
Widest single gap
MMMU Pro (Vals AI): Claude Haiku 4.5 46.1% against Claude Sonnet 4.5 79.3%, 33.2 points apart on a 0 to 100 scale.
Output price
Claude Haiku 4.5 $5.00 against Claude Sonnet 4.5 $15.00 per million output tokens, 3.0x apart.
Context window
Claude Haiku 4.5 takes 200K tokens, Claude Sonnet 4.5 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 4.5Ties
Coding013
Intelligence02
Agentic work04
Reasoning09
Math06
Knowledge013
Web design08
General121
All shared boards176
CodingLike-for-likeSix of these boards feed the Vibe Coding Index013
Coding benchmarks for Claude Haiku 4.5 and Claude Sonnet 4.5
BenchmarkClaude Haiku 4.5Claude Sonnet 4.5Leader
SWE-bench Verified66.6%74.8%Claude Sonnet 4.5
SWE-bench Multilingual64.7%67.0%Claude Sonnet 4.5
LiveBench coding48.1%Not measuredOnly Claude Haiku 4.5 measured
LMArena WebDev13301394Claude Sonnet 4.5
AA Coding Index43.952.1Claude Sonnet 4.5
LiveCodeBench (Vals AI)41.2%73.0%Claude Sonnet 4.5
SWE-bench Verified (Vals AI)66.6%70.0%Claude Sonnet 4.5
Vibe Code Bench (Vals AI)11.4%22.6%Claude Sonnet 4.5
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
Terminal-Bench35.5%46.5%Claude Sonnet 4.5
GSO-BenchNot measured14.7%Only Claude Sonnet 4.5 measured
WeirdML45.4%47.7%Claude Sonnet 4.5
CybenchNot measured60.0%Only Claude Sonnet 4.5 measured
LMArena Text: coding14541488Claude Sonnet 4.5
LMArena Text: software and IT14391473Claude Sonnet 4.5
LMArena WebDev: React13261386Claude Sonnet 4.5
LMArena WebDev: HTML13181399Claude Sonnet 4.5
Neither model has a result on the other 20 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Claude Haiku 4.5 and Claude Sonnet 4.5
BenchmarkClaude Haiku 4.5Claude Sonnet 4.5Leader
AA Intelligence Index16.920.7Claude Sonnet 4.5
Epoch Capabilities Index142.2146.7Claude Sonnet 4.5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index04
Agentic work benchmarks for Claude Haiku 4.5 and Claude Sonnet 4.5
BenchmarkClaude Haiku 4.5Claude Sonnet 4.5Leader
AA Agentic Index8.015.8Claude Sonnet 4.5
Design Arena: agents building web appsNot measured1060Only Claude Sonnet 4.5 measured
Design Arena: agents building full-stack appsNot measured1050Only Claude Sonnet 4.5 measured
Design Arena: agents building mobile appsNot measured1137Only Claude Sonnet 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
METR time horizonsNot measured67.4%Only Claude Sonnet 4.5 measured
Remote Labor IndexNot measured2.1%Only Claude Sonnet 4.5 measured
GDPvalNot measured42.5%Only Claude Sonnet 4.5 measured
BALROG31.2%Not measuredOnly Claude Haiku 4.5 measured
DeepResearch Bench45.5%52.6%Claude Sonnet 4.5
OSWorldNot measured62.9%Only Claude Sonnet 4.5 measured
Vending-Bench 2$459$3,839Claude Sonnet 4.5
Berkeley Function Calling Leaderboard (BFCL)68.7%73.2%Claude Sonnet 4.5
Neither model has a result on the other 22 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index09
Reasoning benchmarks for Claude Haiku 4.5 and Claude Sonnet 4.5
BenchmarkClaude Haiku 4.5Claude Sonnet 4.5Leader
GPQA Diamond72.2%81.6%Claude Sonnet 4.5
LiveBench reasoning61.7%Not measuredOnly Claude Haiku 4.5 measured
MMMU Pro (Vals AI)46.1%79.3%Claude Sonnet 4.5
GPQA Diamond (Epoch AI run)71.2%82.3%Claude Sonnet 4.5
ARC-AGI47.7%63.7%Claude Sonnet 4.5
ARC-AGI-24.0%13.6%Claude Sonnet 4.5
SimpleBenchNot measured54.3%Only Claude Sonnet 4.5 measured
Chess puzzles8.0%10.0%Claude Sonnet 4.5
Mystery game puzzlesNot measured17.0%Only Claude Sonnet 4.5 measured
EBR-benchNot measured2.4%Only Claude Sonnet 4.5 measured
VPCTNot measured39.8%Only Claude Sonnet 4.5 measured
LMArena Text: hard prompts14211462Claude Sonnet 4.5
LMArena Text: expert14431483Claude Sonnet 4.5
LMArena Text: hard prompts in English14351471Claude Sonnet 4.5
Kagi LLM BenchmarkNot measured57.9%Only Claude Sonnet 4.5 measured
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index06
Math benchmarks for Claude Haiku 4.5 and Claude Sonnet 4.5
BenchmarkClaude Haiku 4.5Claude Sonnet 4.5Leader
AIME82.7%88.2%Claude Sonnet 4.5
MGSM (Vals AI)92.2%94.3%Claude Sonnet 4.5
OTIS Mock AIME66.7%77.8%Claude Sonnet 4.5
FrontierMath, tiers 1 to 3Not measured23.9%Only Claude Sonnet 4.5 measured
FrontierMath, tier 4Not measured2.4%Only Claude Sonnet 4.5 measured
ProofBenchNot measured19.0%Only Claude Sonnet 4.5 measured
MATH level 596.4%97.7%Claude Sonnet 4.5
LMArena Text: math13981449Claude Sonnet 4.5
LMArena Text: mathematical work14301462Claude Sonnet 4.5
Neither model has a result on the other 4 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index013
Knowledge benchmarks for Claude Haiku 4.5 and Claude Sonnet 4.5
BenchmarkClaude Haiku 4.5Claude Sonnet 4.5Leader
MMLU Pro78.7%87.4%Claude Sonnet 4.5
LegalBench (Vals AI)81.2%84.1%Claude Sonnet 4.5
CaseLaw (Vals AI)56.5%62.2%Claude Sonnet 4.5
CorpFin (Vals AI)60.6%62.0%Claude Sonnet 4.5
TaxEval (Vals AI)67.5%73.3%Claude Sonnet 4.5
MortgageTax (Vals AI)62.2%64.0%Claude Sonnet 4.5
MedQA (Vals AI)79.6%94.7%Claude Sonnet 4.5
MedCode (Vals AI)32.7%44.1%Claude Sonnet 4.5
SimpleQA Verified13.2%30.7%Claude Sonnet 4.5
LMArena Text: science14061448Claude Sonnet 4.5
LMArena Text: medicine and healthcare13941444Claude Sonnet 4.5
LMArena Text: legal and government14001451Claude Sonnet 4.5
LMArena Text: business and finance14001440Claude Sonnet 4.5
FACTS Benchmark SuiteNot measured40.6%Only Claude Sonnet 4.5 measured
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index08
Web design benchmarks for Claude Haiku 4.5 and Claude Sonnet 4.5
BenchmarkClaude Haiku 4.5Claude Sonnet 4.5Leader
Design Arena: websites11221189Claude Sonnet 4.5
Design Arena: UI components10971170Claude Sonnet 4.5
Design Arena: game dev10961166Claude Sonnet 4.5
Design Arena: data viz11241167Claude Sonnet 4.5
Design Arena: 3D10711157Claude Sonnet 4.5
Design Arena: all code categories11141182Claude Sonnet 4.5
Design Arena: SVG10251114Claude Sonnet 4.5
Design Arena: ASCII art11401205Claude Sonnet 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 Claude Sonnet 4.5
BenchmarkClaude Haiku 4.5Claude Sonnet 4.5Leader
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%36.1%Claude Sonnet 4.5
MedScribe (Vals AI)85.2%84.5%Claude Haiku 4.5
Vals Multimodal Index42.9%Not measuredOnly Claude Haiku 4.5 measured
DTBench73.6%83.2%Claude Sonnet 4.5
LMCA30.9%38.8%Claude Sonnet 4.5
ExploitBench13.7%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text13971438Claude Sonnet 4.5
LMArena Text: instruction following14141459Claude Sonnet 4.5
LMArena Text: creative writing13711442Claude Sonnet 4.5
LMArena Text: English14141450Claude Sonnet 4.5
LMArena Text: non-English13771425Claude Sonnet 4.5
LMArena Text: Chinese14181460Claude Sonnet 4.5
LMArena Text: German13741427Claude Sonnet 4.5
LMArena Text: Japanese13381390Claude Sonnet 4.5
LMArena Text: Korean13461402Claude Sonnet 4.5
LMArena Text: French14111459Claude Sonnet 4.5
LMArena Text: Spanish14211458Claude Sonnet 4.5
LMArena Text: Russian13811437Claude Sonnet 4.5
LMArena Text: Polish13431423Claude Sonnet 4.5
LMArena Text: multi-turn14091465Claude Sonnet 4.5
LMArena Text: longer queries14271475Claude Sonnet 4.5
LMArena Text: writing and language13861442Claude Sonnet 4.5
LMArena Text: entertainment and media13691428Claude Sonnet 4.5
LMArena Document14201450Claude Sonnet 4.5
Neither model has a result on the other 20 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 4.5
BenchmarkClaude Haiku 4.5Claude Sonnet 4.5Leader
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 4.5$0.011Fits 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 4.5$0.195Fits 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 4.5$0.750Fits 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 4.5
SpecificationAnthropic Claude Haiku 4.5Anthropic Claude Sonnet 4.5
MakerAnthropicAnthropic
WeightsNo public weights listedNo public weights listed
ReleasedOctober 15, 2025September 29, 2025
Context window200K1M
Input $/Mtok$1.00$3.00
Output $/Mtok$5.00$15.00
Coding index35.639.5
Independent measurements behind it43
Cost per solved task$0.56$1.16
SourceOpenRouter listingOpenRouter listing

Questions

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

Pick Claude Sonnet 4.5 for coding: it scores 39.5 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 3.0x cheaper ($5.00 vs $15.00 per million) and a lower cost per solved task ($0.56 against $1.16).

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

Claude Haiku 4.5 costs $1.00 per million input tokens and $5.00 per million output tokens; Claude Sonnet 4.5 costs $3.00 and $15.00. Per solved SWE-bench Verified task, Claude Haiku 4.5 costs $0.56 and Claude Sonnet 4.5 $1.16.

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

Claude Sonnet 4.5, with 1M tokens against 200K.

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

77 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 4.5'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-claude-sonnet-4-5" title="Claude Haiku 4.5 vs Claude Sonnet 4.5, 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-4-5">LLMBenchmark.ai, Claude Haiku 4.5 vs Claude Sonnet 4.5</a></p>