Enter opens the highlighted result. Esc closes.

Claude Haiku 4.5 vs Claude Opus 4.6

Claude Opus 4.6 leads Claude Haiku 4.5 on coding, 57.2 to 35.6 on the Vibe Coding Index, and Claude Haiku 4.5 costs 5.0x less per output token ($5.00 vs $25.00 per million). Updated October 22, 2026; 72 benchmarks have a result for both.

Replace Claude Haiku 4.5 Replace Claude Opus 4.6
Claude Haiku 4.5Anthropic
Coding
35.6
Overall
41.0
Output $/M
$5.00
0
Claude Opus 4.6Anthropic
Coding
57.2
Overall
66.0
Output $/M
$25.00
72
vs boards won of 72 shared

Claude Haiku 4.5 or Claude Opus 4.6: which to pick

Pick Claude Opus 4.6 for coding: it scores 57.2 on the Vibe Coding Index against 35.6 for Claude Haiku 4.5.

Pick Claude Haiku 4.5 for output tokens 5.0x cheaper ($5.00 vs $25.00 per million) and a lower cost per solved task ($0.56 against $1.56).

Model AClaude Haiku 4.5Anthropic35.6/1004 independent benchmarks$0.56 per solved taskModel BClaude Opus 4.6Anthropic57.2/1004 independent benchmarks$1.56 per solved task
Shared results
72
Claude Haiku 4.5 only
23
Claude Opus 4.6 only
38
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 Opus 4.6 57.2 from 4 benchmarks.
Widest category
Agentic work, 28.5 points apart on average over 2 shared benchmarks.
Widest single gap
ARC-AGI-2: Claude Haiku 4.5 4.0% against Claude Opus 4.6 69.2%, 65.1 points apart on a 0 to 100 scale.
Output price
Claude Haiku 4.5 $5.00 against Claude Opus 4.6 $25.00 per million output tokens, 5.0x apart.
Context window
Claude Haiku 4.5 takes 200K tokens, Claude Opus 4.6 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 Opus 4.6Ties
Coding012
Intelligence02
Agentic work02
Reasoning09
Math04
Knowledge013
Web design08
General022
All shared boards072
CodingLike-for-likeSix of these boards feed the Vibe Coding Index012
Coding benchmarks for Claude Haiku 4.5 and Claude Opus 4.6
BenchmarkClaude Haiku 4.5Claude Opus 4.6Leader
SWE-bench Verified66.6%75.6%Claude Opus 4.6
SWE-bench Multilingual64.7%72.0%Claude Opus 4.6
LiveBench coding48.1%Not measuredOnly Claude Haiku 4.5 measured
LMArena WebDev13301547Claude Opus 4.6
AA Coding Index43.9Not measuredOnly Claude Haiku 4.5 measured
LiveCodeBench (Vals AI)41.2%84.7%Claude Opus 4.6
SWE-bench Verified (Vals AI)66.6%78.2%Claude Opus 4.6
Vibe Code Bench (Vals AI)11.4%57.6%Claude Opus 4.6
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-Bench Hard (Artificial Analysis run)Not measured48.5%Only Claude Opus 4.6 measured
Terminal-Bench35.5%79.8%Claude Opus 4.6
FrontierCodeNot measured26.6%Only Claude Opus 4.6 measured
GSO-BenchNot measured41.2%Only Claude Opus 4.6 measured
WeirdML45.4%78.0%Claude Opus 4.6
CybenchNot measured93.0%Only Claude Opus 4.6 measured
LMArena Text: coding14541534Claude Opus 4.6
LMArena Text: software and IT14391527Claude Opus 4.6
LMArena WebDev: React13261539Claude Opus 4.6
LMArena WebDev: HTML13181559Claude Opus 4.6
LMArena WebDev: from an imageNot measured1543Only Claude Opus 4.6 measured
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 Claude Opus 4.6
BenchmarkClaude Haiku 4.5Claude Opus 4.6Leader
AA Intelligence Index16.931.9Claude Opus 4.6
Epoch Capabilities Index142.2155.7Claude Opus 4.6
Agentic workLike-for-likePublic boards, shown as published, kept out of the index02
Agentic work benchmarks for Claude Haiku 4.5 and Claude Opus 4.6
BenchmarkClaude Haiku 4.5Claude Opus 4.6Leader
AA Agentic Index8.0Not measuredOnly Claude Haiku 4.5 measured
Design Arena: agents building web appsNot measured1206Only Claude Opus 4.6 measured
Design Arena: agents building full-stack appsNot measured1220Only Claude Opus 4.6 measured
Design Arena: agents building mobile appsNot measured1207Only Claude Opus 4.6 measured
Design Arena: agents building Android appsNot measured1197Only Claude Opus 4.6 measured
Design Arena: agents building gamesNot measured1212Only Claude Opus 4.6 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 measured92.1%Only Claude Opus 4.6 measured
APEX-AgentsNot measured46.3%Only Claude Opus 4.6 measured
METR time horizonsNot measured78.9%Only Claude Opus 4.6 measured
Remote Labor IndexNot measured4.2%Only Claude Opus 4.6 measured
BALROG31.2%Not measuredOnly Claude Haiku 4.5 measured
DeepResearch Bench45.5%55.3%Claude Opus 4.6
Vending-Bench 2$459$8,018Claude Opus 4.6
Berkeley Function Calling Leaderboard (BFCL)68.7%Not measuredOnly Claude Haiku 4.5 measured
Neither model has a result on the other 20 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index09
Reasoning benchmarks for Claude Haiku 4.5 and Claude Opus 4.6
BenchmarkClaude Haiku 4.5Claude Opus 4.6Leader
GPQA Diamond72.2%89.7%Claude Opus 4.6
LiveBench reasoning61.7%Not measuredOnly Claude Haiku 4.5 measured
MMMU Pro (Vals AI)46.1%83.9%Claude Opus 4.6
GPQA Diamond (Artificial Analysis run)Not measured89.6%Only Claude Opus 4.6 measured
Humanity's Last Exam (Artificial Analysis run)Not measured39.9%Only Claude Opus 4.6 measured
GPQA Diamond (Epoch AI run)71.2%90.5%Claude Opus 4.6
ARC-AGI47.7%94.0%Claude Opus 4.6
ARC-AGI-24.0%69.2%Claude Opus 4.6
SimpleBenchNot measured67.6%Only Claude Opus 4.6 measured
Chess puzzles8.0%21.0%Claude Opus 4.6
Mystery game puzzlesNot measured25.0%Only Claude Opus 4.6 measured
EBR-benchNot measured12.7%Only Claude Opus 4.6 measured
LMArena Text: hard prompts14211525Claude Opus 4.6
LMArena Text: expert14431544Claude Opus 4.6
LMArena Text: hard prompts in English14351530Claude Opus 4.6
LMArena Vision: diagramsNot measured1340Only Claude Opus 4.6 measured
LMArena Vision: homeworkNot measured1337Only Claude Opus 4.6 measured
Kagi LLM BenchmarkNot measured83.6%Only Claude Opus 4.6 measured
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index04
Math benchmarks for Claude Haiku 4.5 and Claude Opus 4.6
BenchmarkClaude Haiku 4.5Claude Opus 4.6Leader
AIME82.7%95.6%Claude Opus 4.6
MGSM (Vals AI)92.2%Not measuredOnly Claude Haiku 4.5 measured
OTIS Mock AIME66.7%94.4%Claude Opus 4.6
FrontierMath, tiers 1 to 3Not measured66.0%Only Claude Opus 4.6 measured
FrontierMath, tier 4Not measured26.8%Only Claude Opus 4.6 measured
ProofBenchNot measured50.0%Only Claude Opus 4.6 measured
MATH level 596.4%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text: math13981518Claude Opus 4.6
LMArena Text: mathematical work14301525Claude Opus 4.6
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 Opus 4.6
BenchmarkClaude Haiku 4.5Claude Opus 4.6Leader
MMLU Pro78.7%89.1%Claude Opus 4.6
LegalBench (Vals AI)81.2%85.3%Claude Opus 4.6
CaseLaw (Vals AI)56.5%62.1%Claude Opus 4.6
CorpFin (Vals AI)60.6%67.0%Claude Opus 4.6
TaxEval (Vals AI)67.5%76.0%Claude Opus 4.6
MortgageTax (Vals AI)62.2%68.5%Claude Opus 4.6
MedQA (Vals AI)79.6%95.4%Claude Opus 4.6
MedCode (Vals AI)32.7%49.1%Claude Opus 4.6
SimpleQA Verified13.2%47.0%Claude Opus 4.6
LMArena Text: science14061519Claude Opus 4.6
LMArena Text: medicine and healthcare13941504Claude Opus 4.6
LMArena Text: legal and government14001512Claude Opus 4.6
LMArena Text: business and finance14001497Claude Opus 4.6
FACTS Benchmark SuiteNot measured41.5%Only Claude Opus 4.6 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 Opus 4.6
BenchmarkClaude Haiku 4.5Claude Opus 4.6Leader
Design Arena: websites11221291Claude Opus 4.6
Design Arena: UI components10971281Claude Opus 4.6
Design Arena: game dev10971277Claude Opus 4.6
Design Arena: data viz11241279Claude Opus 4.6
Design Arena: 3D10711273Claude Opus 4.6
Design Arena: all code categories11141288Claude Opus 4.6
Design Arena: SVG10251227Claude Opus 4.6
Design Arena: ASCII art11401255Claude Opus 4.6
LiveBench design59.9%Not measuredOnly Claude Haiku 4.5 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index022
General benchmarks for Claude Haiku 4.5 and Claude Opus 4.6
BenchmarkClaude Haiku 4.5Claude Opus 4.6Leader
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%51.6%Claude Opus 4.6
MedScribe (Vals AI)85.2%86.7%Claude Opus 4.6
Vals Multimodal Index42.9%Not measuredOnly Claude Haiku 4.5 measured
IFBenchNot measured53.1%Only Claude Opus 4.6 measured
Long context reasoning (AA-LCR)Not measured78.0%Only Claude Opus 4.6 measured
DTBench73.6%91.2%Claude Opus 4.6
LMCA30.9%55.8%Claude Opus 4.6
CL-benchNot measured20.7%Only Claude Opus 4.6 measured
Furniture assemblyNot measured28.3%Only Claude Opus 4.6 measured
ExploitBench13.7%Not measuredOnly Claude Haiku 4.5 measured
CL-bench LifeNot measured17.0%Only Claude Opus 4.6 measured
LMArena Text13971501Claude Opus 4.6
LMArena Text: instruction following14141521Claude Opus 4.6
LMArena Text: creative writing13711505Claude Opus 4.6
LMArena VisionNot measured1316Only Claude Opus 4.6 measured
LMArena Text: English14141511Claude Opus 4.6
LMArena Text: non-English13771488Claude Opus 4.6
LMArena Text: Chinese14181551Claude Opus 4.6
LMArena Text: German13741500Claude Opus 4.6
LMArena Text: Japanese13381488Claude Opus 4.6
LMArena Text: Korean13461464Claude Opus 4.6
LMArena Text: French14111512Claude Opus 4.6
LMArena Text: Spanish14211510Claude Opus 4.6
LMArena Text: Russian13811497Claude Opus 4.6
LMArena Text: Polish13431499Claude Opus 4.6
LMArena Text: multi-turn14091511Claude Opus 4.6
LMArena Text: longer queries14271518Claude Opus 4.6
LMArena Text: writing and language13861502Claude Opus 4.6
LMArena Text: entertainment and media13691492Claude Opus 4.6
LMArena Vision: EnglishNot measured1324Only Claude Opus 4.6 measured
LMArena Vision: ChineseNot measured1370Only Claude Opus 4.6 measured
LMArena Vision: reading textNot measured1326Only Claude Opus 4.6 measured
LMArena Vision: humorNot measured1314Only Claude Opus 4.6 measured
LMArena Vision: recognizing thingsNot measured1274Only Claude Opus 4.6 measured
LMArena Vision: creative writingNot measured1331Only Claude Opus 4.6 measured
LMArena Document14201507Claude Opus 4.6
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 Claude Opus 4.6
BenchmarkClaude Haiku 4.5Claude Opus 4.6Leader
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 Opus 4.6$0.018Fits 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 Opus 4.6$0.325Fits 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 Opus 4.6$1.25Fits 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 Opus 4.6
SpecificationAnthropic Claude Haiku 4.5Anthropic Claude Opus 4.6
MakerAnthropicAnthropic
WeightsNo public weights listedNo public weights listed
ReleasedOctober 15, 2025February 4, 2026
Context window200K1M
Input $/Mtok$1.00$5.00
Output $/Mtok$5.00$25.00
Coding index35.657.2
Independent measurements behind it44
Cost per solved task$0.56$1.56
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Haiku 4.5 better than Claude Opus 4.6 for coding?

Pick Claude Opus 4.6 for coding: it scores 57.2 on the Vibe Coding Index against 35.6 for Claude Haiku 4.5. Pick Claude Haiku 4.5 for output tokens 5.0x cheaper ($5.00 vs $25.00 per million) and a lower cost per solved task ($0.56 against $1.56).

Which is cheaper, Claude Haiku 4.5 or Claude Opus 4.6?

Claude Haiku 4.5 costs $1.00 per million input tokens and $5.00 per million output tokens; Claude Opus 4.6 costs $5.00 and $25.00. Per solved SWE-bench Verified task, Claude Haiku 4.5 costs $0.56 and Claude Opus 4.6 $1.56.

Which has the bigger context window, Claude Haiku 4.5 or Claude Opus 4.6?

Claude Opus 4.6, with 1M tokens against 200K.

How many benchmarks is the Claude Haiku 4.5 vs Claude Opus 4.6 comparison based on?

72 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 Opus 4.6's on 4. 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-opus-4-6" title="Claude Haiku 4.5 vs Claude Opus 4.6, 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-opus-4-6">LLMBenchmark.ai, Claude Haiku 4.5 vs Claude Opus 4.6</a></p>