LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Claude Haiku 4.5 vs Llama 4 Maverick

Updated October 21, 2026. 58 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 Llama 4 Maverick
Claude Haiku 4.5Anthropic
Coding
49.8
Overall
16.9
Output $/M
$5.00
52
Llama 4 MaverickMeta Llama
Coding
18.1
Overall
9.3
Output $/M
$0.6525
6
vs boards won of 58 shared

Decision reading

Pick Claude Haiku 4.5 for coding: it scores 49.8 on the Vibe Coding Index against 18.1 for Llama 4 Maverick.

Pick Llama 4 Maverick when output tokens cost 7.7x less, or when the context window is larger, 524K against 200K tokens.

Model AClaude Haiku 4.5Anthropic49.8/1003 independent benchmarks$0.56 per solved taskModel BLlama 4 MaverickMeta Llama18.1/1002 independent benchmarks$1.491 per solved task
Shared results
58
Claude Haiku 4.5 only
36
Llama 4 Maverick only
26
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, Llama 4 Maverick 18.1 from 2 benchmarks.
Widest category
Web design, 28.3 points apart on average over 6 shared benchmarks.
Widest single gap
AIME: Claude Haiku 4.5 82.7% against Llama 4 Maverick 25.2%, 57.5 points apart on a 0 to 100 scale.
Output price
Claude Haiku 4.5 $5.00 against Llama 4 Maverick $0.6525 per million output tokens, 7.7x apart.
Context window
Claude Haiku 4.5 takes 200K tokens, Llama 4 Maverick 524K.

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 4.5BarsLlama 4 MaverickTies
Coding51
Intelligence20
Agentic work10
Reasoning61
Math31
Knowledge92
Web design60
General201
All shared boards526
CodingLike-for-likeFour of these boards feed the Vibe Coding Index51
Coding benchmarks for Claude Haiku 4.5 and Llama 4 Maverick
BenchmarkClaude Haiku 4.5Llama 4 MaverickLeader
Aider polyglotNot measured15.6%Only Llama 4 Maverick measured
SWE-bench Verified66.6%21.0%Claude Haiku 4.5
SWE-bench Multilingual64.7%Not measuredOnly Claude Haiku 4.5 measured
LiveBench coding48.1%Not measuredOnly Claude Haiku 4.5 measured
LMArena WebDev1330Not measuredOnly Claude Haiku 4.5 measured
AA Coding Index43.916.3Claude Haiku 4.5
LiveCodeBench (Vals AI)41.2%47.3%Llama 4 Maverick
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
LiveCodeBench (Artificial Analysis run)Not measured39.7%Only Llama 4 Maverick measured
SciCodeNot measured31.7%Only Llama 4 Maverick measured
Terminal-Bench Hard (Artificial Analysis run)Not measured6.8%Only Llama 4 Maverick measured
Terminal-Bench35.5%Not measuredOnly Claude Haiku 4.5 measured
WeirdML45.4%24.5%Claude Haiku 4.5
ALE-BenchNot measured173.0Only Llama 4 Maverick measured
LMArena Text: coding14541301Claude Haiku 4.5
LMArena Text: software and IT14391299Claude Haiku 4.5
LMArena WebDev: React1326Not measuredOnly Claude Haiku 4.5 measured
LMArena WebDev: HTML1318Not measuredOnly Claude Haiku 4.5 measured
Neither model has a result on the other 16 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Haiku 4.5 and Llama 4 Maverick
BenchmarkClaude Haiku 4.5Llama 4 MaverickLeader
AA Intelligence Index16.99.3Claude Haiku 4.5
Epoch Capabilities Index142.2132.2Claude Haiku 4.5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for Claude Haiku 4.5 and Llama 4 Maverick
BenchmarkClaude Haiku 4.5Llama 4 MaverickLeader
AA Agentic Index8.00.6Claude Haiku 4.5
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 measured17.8%Only Llama 4 Maverick measured
BALROG31.2%Not measuredOnly Claude Haiku 4.5 measured
DeepResearch Bench45.5%Not measuredOnly Claude Haiku 4.5 measured
Vending-Bench 2$459Not measuredOnly Claude Haiku 4.5 measured
Neither model has a result on the other 27 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index61
Reasoning benchmarks for Claude Haiku 4.5 and Llama 4 Maverick
BenchmarkClaude Haiku 4.5Llama 4 MaverickLeader
GPQA Diamond72.2%69.4%Claude Haiku 4.5
LiveBench reasoning61.7%Not measuredOnly Claude Haiku 4.5 measured
MMMU Pro (Vals AI)46.1%71.7%Llama 4 Maverick
GPQA Diamond (Artificial Analysis run)Not measured67.1%Only Llama 4 Maverick measured
Humanity's Last Exam (Artificial Analysis run)Not measured4.9%Only Llama 4 Maverick measured
GPQA Diamond (Epoch AI run)71.2%Not measuredOnly Claude Haiku 4.5 measured
ARC-AGI47.7%4.4%Claude Haiku 4.5
ARC-AGI-24.0%0.0%Claude Haiku 4.5
SimpleBenchNot measured27.7%Only Llama 4 Maverick measured
Chess puzzles8.0%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text: hard prompts14211281Claude Haiku 4.5
LMArena Text: expert14431259Claude Haiku 4.5
LMArena Text: hard prompts in English14351295Claude Haiku 4.5
LMArena Vision: diagramsNot measured1134Only Llama 4 Maverick measured
LMArena Vision: homeworkNot measured1164Only Llama 4 Maverick measured
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index31
Math benchmarks for Claude Haiku 4.5 and Llama 4 Maverick
BenchmarkClaude Haiku 4.5Llama 4 MaverickLeader
AIME82.7%25.2%Claude Haiku 4.5
MATH 500 (Vals AI)Not measured85.2%Only Llama 4 Maverick measured
MGSM (Vals AI)92.2%92.4%Llama 4 Maverick
AA Math IndexNot measured19.3Only Llama 4 Maverick measured
AIME 2025 (Artificial Analysis run)Not measured19.3%Only Llama 4 Maverick measured
OTIS Mock AIME66.7%Not measuredOnly Claude Haiku 4.5 measured
MATH level 596.4%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text: math13981299Claude Haiku 4.5
LMArena Text: mathematical work14301295Claude Haiku 4.5
Neither model has a result on the other 4 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index92
Knowledge benchmarks for Claude Haiku 4.5 and Llama 4 Maverick
BenchmarkClaude Haiku 4.5Llama 4 MaverickLeader
MMLU Pro78.7%79.4%Llama 4 Maverick
LegalBench (Vals AI)81.2%77.8%Claude Haiku 4.5
CaseLaw (Vals AI)56.5%Not measuredOnly Claude Haiku 4.5 measured
CorpFin (Vals AI)60.6%49.7%Claude Haiku 4.5
TaxEval (Vals AI)67.5%66.6%Claude Haiku 4.5
MortgageTax (Vals AI)62.2%58.5%Claude Haiku 4.5
MedQA (Vals AI)79.6%43.3%Claude Haiku 4.5
MedCode (Vals AI)32.7%36.5%Llama 4 Maverick
MMLU Pro (Artificial Analysis run)Not measured80.9%Only Llama 4 Maverick measured
SimpleQA Verified13.2%Not measuredOnly Claude Haiku 4.5 measured
GeoBenchNot measured52.0%Only Llama 4 Maverick measured
LMArena Text: science14061288Claude Haiku 4.5
LMArena Text: medicine and healthcare13941275Claude Haiku 4.5
LMArena Text: legal and government14001286Claude Haiku 4.5
LMArena Text: business and finance14001260Claude 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 index60
Web design benchmarks for Claude Haiku 4.5 and Llama 4 Maverick
BenchmarkClaude Haiku 4.5Llama 4 MaverickLeader
Design Arena: websites1122871Claude Haiku 4.5
Design Arena: UI components1100899Claude Haiku 4.5
Design Arena: game dev1097838Claude Haiku 4.5
Design Arena: data viz1124882Claude Haiku 4.5
Design Arena: 3D1072901Claude Haiku 4.5
Design Arena: all code categories1115880Claude Haiku 4.5
Design Arena: SVG1025Not measuredOnly Claude Haiku 4.5 measured
Design Arena: ASCII art1139Not measuredOnly Claude Haiku 4.5 measured
LiveBench design59.9%Not measuredOnly Claude Haiku 4.5 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index201
General benchmarks for Claude Haiku 4.5 and Llama 4 Maverick
BenchmarkClaude Haiku 4.5Llama 4 MaverickLeader
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%35.7%Llama 4 Maverick
MedScribe (Vals AI)85.2%54.2%Claude Haiku 4.5
Vals Multimodal Index42.9%Not measuredOnly Claude Haiku 4.5 measured
IFBenchNot measured43.0%Only Llama 4 Maverick measured
Long context reasoning (AA-LCR)Not measured50.0%Only Llama 4 Maverick measured
DTBench73.6%61.9%Claude Haiku 4.5
LMCA30.9%15.9%Claude Haiku 4.5
Fiction.LiveBenchNot measured46.2%Only Llama 4 Maverick measured
Creative writing (Lech Mazur)Not measured62.0%Only Llama 4 Maverick measured
ExploitBench13.7%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text13971287Claude Haiku 4.5
LMArena Text: instruction following14141267Claude Haiku 4.5
LMArena Text: creative writing13711266Claude Haiku 4.5
LMArena VisionNot measured1142Only Llama 4 Maverick measured
LMArena Text: English14141303Claude Haiku 4.5
LMArena Text: non-English13771269Claude Haiku 4.5
LMArena Text: Chinese14181277Claude Haiku 4.5
LMArena Text: German13741291Claude Haiku 4.5
LMArena Text: Japanese13381206Claude Haiku 4.5
LMArena Text: Korean13461203Claude Haiku 4.5
LMArena Text: French14111259Claude Haiku 4.5
LMArena Text: Spanish14211293Claude Haiku 4.5
LMArena Text: Russian13811286Claude Haiku 4.5
LMArena Text: Polish13431275Claude Haiku 4.5
LMArena Text: multi-turn14091289Claude Haiku 4.5
LMArena Text: longer queries14271280Claude Haiku 4.5
LMArena Text: writing and language13861277Claude Haiku 4.5
LMArena Text: entertainment and media13691250Claude Haiku 4.5
LMArena Vision: EnglishNot measured1150Only Llama 4 Maverick measured
LMArena Vision: ChineseNot measured1141Only Llama 4 Maverick measured
LMArena Vision: reading textNot measured1143Only Llama 4 Maverick measured
LMArena Vision: humorNot measured1100Only Llama 4 Maverick measured
LMArena Vision: creative writingNot measured1099Only Llama 4 Maverick measured
LMArena Document1420Not measuredOnly Claude Haiku 4.5 measured
Neither model has a result on the other 10 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 Llama 4 Maverick
BenchmarkClaude Haiku 4.5Llama 4 MaverickLeader
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
Llama 4 Maverick$0.0005Fits in one request

Llama 4 Maverick costs less

Repository review

50K input + 3K output tokens

Claude Haiku 4.5$0.065Fits in one request
Llama 4 Maverick$0.011Fits in one request

Llama 4 Maverick costs less

Agent loop

200K input + 10K output tokens

Claude Haiku 4.5$0.250Exceeds the context window
Llama 4 Maverick$0.044Fits in one request

Llama 4 Maverick 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 Llama 4 Maverick
SpecificationAnthropic Claude Haiku 4.5Meta Llama 4 Maverick
MakerAnthropicMeta Llama
WeightsNo public weights listedOpen weights
ReleasedOctober 15, 2025April 5, 2025
Context window200K524K
Input $/Mtok$1.00$0.1875
Output $/Mtok$5.00$0.6525
Coding index49.818.1
Independent measurements behind it32
Cost per solved task$0.56$1.491
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Haiku 4.5 better than Llama 4 Maverick for coding?

Pick Claude Haiku 4.5 for coding: it scores 49.8 on the Vibe Coding Index against 18.1 for Llama 4 Maverick. Pick Llama 4 Maverick when output tokens cost 7.7x less, or when the context window is larger, 524K against 200K tokens.

Which is cheaper, Claude Haiku 4.5 or Llama 4 Maverick?

Claude Haiku 4.5 costs $1.00 per million input tokens and $5.00 per million output tokens; Llama 4 Maverick costs $0.1875 and $0.6525. Per solved SWE-bench Verified task, Claude Haiku 4.5 costs $0.56 and Llama 4 Maverick $1.491.

Which has the bigger context window, Claude Haiku 4.5 or Llama 4 Maverick?

Llama 4 Maverick, with 524K tokens against 200K.

How many benchmarks is the Claude Haiku 4.5 vs Llama 4 Maverick comparison based on?

58 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 Llama 4 Maverick's on 2. 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-llama-4-maverick" title="Claude Haiku 4.5 vs Llama 4 Maverick, 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-llama-4-maverick">LLMBenchmark.ai, Claude Haiku 4.5 vs Llama 4 Maverick</a></p>