LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Claude Haiku 4.5 vs Claude Opus 4.1

Updated October 21, 2026. 60 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 Claude Opus 4.1
Claude Haiku 4.5Anthropic
Coding
49.8
Overall
16.9
Output $/M
$5.00
5
Claude Opus 4.1Anthropic
Coding
27.2
Overall
22.8
Output $/M
$75.00
55
vs boards won of 60 shared

Decision reading

Pick Claude Haiku 4.5 for coding: it scores 49.8 on the Vibe Coding Index against 27.2 for Claude Opus 4.1.

Pick Claude Opus 4.1 when what matters is LMArena WebDev or LiveCodeBench (Vals AI), where it leads.

Model AClaude Haiku 4.5Anthropic49.8/1003 independent benchmarks$0.56 per solved taskModel BClaude Opus 4.1Anthropic27.2/1001 independent benchmarkNo cost per solved task
Shared results
60
Claude Haiku 4.5 only
34
Claude Opus 4.1 only
11
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, Claude Opus 4.1 27.2 from 1 benchmark.
Widest category
Web design, 8.2 points apart on average over 8 shared benchmarks.
Widest single gap
MMMU Pro (Vals AI): Claude Haiku 4.5 46.1% against Claude Opus 4.1 77.5%, 31.4 points apart on a 0 to 100 scale.
Output price
Claude Haiku 4.5 $5.00 against Claude Opus 4.1 $75.00 per million output tokens, 15.0x apart.
Context window
Both take 200K tokens.

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 4.1Ties
Coding07
Intelligence02
Agentic work01
Reasoning15
Math14
Knowledge19
Web design08
General219
All shared boards555
CodingLike-for-likeFour of these boards feed the Vibe Coding Index07
Coding benchmarks for Claude Haiku 4.5 and Claude Opus 4.1
BenchmarkClaude Haiku 4.5Claude Opus 4.1Leader
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%Not measuredOnly Claude Haiku 4.5 measured
LMArena WebDev13301390Claude Opus 4.1
AA Coding Index43.9Not measuredOnly Claude Haiku 4.5 measured
LiveCodeBench (Vals AI)41.2%66.5%Claude Opus 4.1
SWE-bench Verified (Vals AI)66.6%Not measuredOnly Claude Haiku 4.5 measured
Vibe Code Bench (Vals AI)11.4%Not measuredOnly Claude Haiku 4.5 measured
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%38.0%Claude Opus 4.1
WeirdML45.4%45.9%Claude Opus 4.1
CybenchNot measured42.0%Only Claude Opus 4.1 measured
LMArena Text: coding14541479Claude Opus 4.1
LMArena Text: software and IT14391456Claude Opus 4.1
LMArena WebDev: React1326Not measuredOnly Claude Haiku 4.5 measured
LMArena WebDev: HTML13181399Claude Opus 4.1
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 Opus 4.1
BenchmarkClaude Haiku 4.5Claude Opus 4.1Leader
AA Intelligence Index16.922.8Claude Opus 4.1
Epoch Capabilities Index142.2144.1Claude Opus 4.1
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for Claude Haiku 4.5 and Claude Opus 4.1
BenchmarkClaude Haiku 4.5Claude Opus 4.1Leader
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
METR time horizonsNot measured66.8%Only Claude Opus 4.1 measured
GDPvalNot measured43.6%Only Claude Opus 4.1 measured
BALROG31.2%Not measuredOnly Claude Haiku 4.5 measured
DeepResearch Bench45.5%48.3%Claude Opus 4.1
Vending-Bench 2$459Not measuredOnly Claude Haiku 4.5 measured
Neither model has a result on the other 26 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index15
Reasoning benchmarks for Claude Haiku 4.5 and Claude Opus 4.1
BenchmarkClaude Haiku 4.5Claude Opus 4.1Leader
GPQA Diamond72.2%76.3%Claude Opus 4.1
LiveBench reasoning61.7%Not measuredOnly Claude Haiku 4.5 measured
MMMU Pro (Vals AI)46.1%77.5%Claude Opus 4.1
GPQA Diamond (Epoch AI run)71.2%77.3%Claude Opus 4.1
ARC-AGI47.7%Not measuredOnly Claude Haiku 4.5 measured
ARC-AGI-24.0%Not measuredOnly Claude Haiku 4.5 measured
SimpleBenchNot measured60.0%Only Claude Opus 4.1 measured
Chess puzzles8.0%Not measuredOnly Claude Haiku 4.5 measured
Mystery game puzzlesNot measured21.0%Only Claude Opus 4.1 measured
EBR-benchNot measured7.9%Only Claude Opus 4.1 measured
VPCTNot measured35.0%Only Claude Opus 4.1 measured
LMArena Text: hard prompts14211442Claude Opus 4.1
LMArena Text: expert14431438Claude Haiku 4.5
LMArena Text: hard prompts in English14351451Claude Opus 4.1
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index14
Math benchmarks for Claude Haiku 4.5 and Claude Opus 4.1
BenchmarkClaude Haiku 4.5Claude Opus 4.1Leader
AIME82.7%78.2%Claude Haiku 4.5
MATH 500 (Vals AI)Not measured95.4%Only Claude Opus 4.1 measured
MGSM (Vals AI)92.2%94.4%Claude Opus 4.1
OTIS Mock AIME66.7%68.9%Claude Opus 4.1
FrontierMath, tiers 1 to 3Not measured12.6%Only Claude Opus 4.1 measured
FrontierMath, tier 4Not measured2.4%Only Claude Opus 4.1 measured
MATH level 596.4%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text: math13981431Claude Opus 4.1
LMArena Text: mathematical work14301434Claude Opus 4.1
Neither model has a result on the other 4 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index19
Knowledge benchmarks for Claude Haiku 4.5 and Claude Opus 4.1
BenchmarkClaude Haiku 4.5Claude Opus 4.1Leader
MMLU Pro78.7%87.9%Claude Opus 4.1
LegalBench (Vals AI)81.2%83.5%Claude Opus 4.1
CaseLaw (Vals AI)56.5%Not measuredOnly Claude Haiku 4.5 measured
CorpFin (Vals AI)60.6%Not measuredOnly Claude Haiku 4.5 measured
TaxEval (Vals AI)67.5%73.7%Claude Opus 4.1
MortgageTax (Vals AI)62.2%61.1%Claude Haiku 4.5
MedQA (Vals AI)79.6%93.6%Claude Opus 4.1
MedCode (Vals AI)32.7%47.2%Claude Opus 4.1
SimpleQA Verified13.2%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text: science14061422Claude Opus 4.1
LMArena Text: medicine and healthcare13941416Claude Opus 4.1
LMArena Text: legal and government14001421Claude Opus 4.1
LMArena Text: business and finance14001406Claude Opus 4.1
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 4.1
BenchmarkClaude Haiku 4.5Claude Opus 4.1Leader
Design Arena: websites11221177Claude Opus 4.1
Design Arena: UI components11001164Claude Opus 4.1
Design Arena: game dev10971172Claude Opus 4.1
Design Arena: data viz11241166Claude Opus 4.1
Design Arena: 3D10721153Claude Opus 4.1
Design Arena: all code categories11151171Claude Opus 4.1
Design Arena: SVG10251152Claude Opus 4.1
Design Arena: ASCII art11391167Claude Opus 4.1
LiveBench design59.9%Not measuredOnly Claude Haiku 4.5 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index219
General benchmarks for Claude Haiku 4.5 and Claude Opus 4.1
BenchmarkClaude Haiku 4.5Claude Opus 4.1Leader
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%31.4%Claude Haiku 4.5
MedScribe (Vals AI)85.2%73.9%Claude Haiku 4.5
Vals Multimodal Index42.9%Not measuredOnly Claude Haiku 4.5 measured
DTBench73.6%80.0%Claude Opus 4.1
LMCA30.9%37.1%Claude Opus 4.1
Creative writing (Lech Mazur)Not measured84.7%Only Claude Opus 4.1 measured
ExploitBench13.7%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text13971419Claude Opus 4.1
LMArena Text: instruction following14141435Claude Opus 4.1
LMArena Text: creative writing13711412Claude Opus 4.1
LMArena Text: English14141433Claude Opus 4.1
LMArena Text: non-English13771405Claude Opus 4.1
LMArena Text: Chinese14181427Claude Opus 4.1
LMArena Text: German13741413Claude Opus 4.1
LMArena Text: Japanese13381377Claude Opus 4.1
LMArena Text: Korean13461381Claude Opus 4.1
LMArena Text: French14111433Claude Opus 4.1
LMArena Text: Spanish14211448Claude Opus 4.1
LMArena Text: Russian13811422Claude Opus 4.1
LMArena Text: Polish13431413Claude Opus 4.1
LMArena Text: multi-turn14091444Claude Opus 4.1
LMArena Text: longer queries14271455Claude Opus 4.1
LMArena Text: writing and language13861418Claude Opus 4.1
LMArena Text: entertainment and media13691398Claude Opus 4.1
LMArena Document1420Not measuredOnly Claude Haiku 4.5 measured
Neither model has a result on the other 19 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 4.1
BenchmarkClaude Haiku 4.5Claude Opus 4.1Leader
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
Claude Opus 4.1$0.052Fits 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 4.1$0.975Fits 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 4.1$3.75Exceeds the context window

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 4.1
SpecificationAnthropic Claude Haiku 4.5Anthropic Claude Opus 4.1
MakerAnthropicAnthropic
WeightsNo public weights listedNo public weights listed
ReleasedOctober 15, 2025August 5, 2025
Context window200K200K
Input $/Mtok$1.00$15.00
Output $/Mtok$5.00$75.00
Coding index49.827.2
Independent measurements behind it31
Cost per solved task$0.56Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Haiku 4.5 better than Claude Opus 4.1 for coding?

Pick Claude Haiku 4.5 for coding: it scores 49.8 on the Vibe Coding Index against 27.2 for Claude Opus 4.1. Pick Claude Opus 4.1 when what matters is LMArena WebDev or LiveCodeBench (Vals AI), where it leads.

Which is cheaper, Claude Haiku 4.5 or Claude Opus 4.1?

Claude Haiku 4.5 costs $1.00 per million input tokens and $5.00 per million output tokens; Claude Opus 4.1 costs $15.00 and $75.00. Cost per solved task is known for Claude Haiku 4.5 only.

Which has the bigger context window, Claude Haiku 4.5 or Claude Opus 4.1?

Neither: both take 200K tokens.

How many benchmarks is the Claude Haiku 4.5 vs Claude Opus 4.1 comparison based on?

60 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 Claude Opus 4.1's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next