LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Claude Haiku 4.5 vs GPT-6 Luna

Updated October 21, 2026. 68 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 GPT-6 Luna
Claude Haiku 4.5Anthropic
Coding
49.8
Overall
16.9
Output $/M
$5.00
21
GPT-6 LunaOpenAI
Coding
71.4
Overall
38.1
Output $/M
$0.50
47
vs boards won of 68 shared

Decision reading

Pick GPT-6 Luna for coding: it scores 71.4 on the Vibe Coding Index against 49.8 for Claude Haiku 4.5, though on 2 benchmarks against 3.

Pick Claude Haiku 4.5 when what matters is LMArena Text: coding or LMArena Text: software and IT, where it leads.

Model AClaude Haiku 4.5Anthropic49.8/1003 independent benchmarks$0.56 per solved taskModel BGPT-6 LunaOpenAI71.4/1002 independent benchmarksNo cost per solved task
Shared results
68
Claude Haiku 4.5 only
26
GPT-6 Luna only
34
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, GPT-6 Luna 71.4 from 2 benchmarks.
Widest category
Coding, 30.0 points apart on average over 10 shared benchmarks.
Widest single gap
Vibe Code Bench (Vals AI): Claude Haiku 4.5 11.4% against GPT-6 Luna 81.7%, 70.3 points apart on a 0 to 100 scale.
Output price
Claude Haiku 4.5 $5.00 against GPT-6 Luna $0.50 per million output tokens, 10.0x apart.
Context window
Claude Haiku 4.5 takes 200K tokens, GPT-6 Luna 1.05M.

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 4.5BarsGPT-6 LunaTies
Coding28
Intelligence02
Agentic work07
Reasoning35
Math12
Knowledge42
Web design09
General1112
All shared boards2147
CodingLike-for-likeFour of these boards feed the Vibe Coding Index28
Coding benchmarks for Claude Haiku 4.5 and GPT-6 Luna
BenchmarkClaude Haiku 4.5GPT-6 LunaLeader
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%84.5%GPT-6 Luna
LMArena WebDev13301578GPT-6 Luna
AA Coding Index43.9Not measuredOnly Claude Haiku 4.5 measured
LiveCodeBench (Vals AI)41.2%Not measuredOnly Claude Haiku 4.5 measured
SWE-bench Verified (Vals AI)66.6%Not measuredOnly Claude Haiku 4.5 measured
Terminal-Bench 4 (Vals AI)Not measured13.6%Only GPT-6 Luna measured
Vibe Code Bench (Vals AI)11.4%81.7%GPT-6 Luna
Code migration (Vals AI)7.5%42.5%GPT-6 Luna
ProgramBench (Vals AI)0.0%0.5%GPT-6 Luna
IOI (Vals AI)Not measured55.6%Only GPT-6 Luna measured
Terminal-Bench 2.1 (Vals AI)43.8%73.0%GPT-6 Luna
SWE-bench Multimodal (Vals AI)Not measured37.5%Only GPT-6 Luna measured
CyberBench (Vals AI)Not measured76.3%Only GPT-6 Luna measured
SciCodeNot measured54.6%Only GPT-6 Luna measured
Terminal-Bench35.5%Not measuredOnly Claude Haiku 4.5 measured
FrontierCodeNot measured42.4%Only GPT-6 Luna measured
WeirdML45.4%Not measuredOnly Claude Haiku 4.5 measured
ALE-BenchNot measured1576.9Only GPT-6 Luna measured
LMArena Text: coding14541437Claude Haiku 4.5
LMArena Text: software and IT14391423Claude Haiku 4.5
LMArena WebDev: React13261573GPT-6 Luna
LMArena WebDev: HTML13181595GPT-6 Luna
LMArena WebDev: from an imageNot measured1571Only GPT-6 Luna measured
Neither model has a result on the other 13 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Claude Haiku 4.5 and GPT-6 Luna
BenchmarkClaude Haiku 4.5GPT-6 LunaLeader
AA Intelligence Index16.938.1GPT-6 Luna
Epoch Capabilities Index142.2156.8GPT-6 Luna
Agentic workLike-for-likePublic boards, shown as published, kept out of the index07
Agentic work benchmarks for Claude Haiku 4.5 and GPT-6 Luna
BenchmarkClaude Haiku 4.5GPT-6 LunaLeader
AA Agentic Index8.0Not measuredOnly Claude Haiku 4.5 measured
Design Arena: agents building web appsNot measured1189Only GPT-6 Luna measured
Design Arena: agents building full-stack appsNot measured1158Only GPT-6 Luna measured
Design Arena: agents building mobile appsNot measured1133Only GPT-6 Luna measured
LiveBench research42.2%43.5%GPT-6 Luna
LiveBench browser40.0%72.0%GPT-6 Luna
LiveBench long agentic11.1%48.1%GPT-6 Luna
SREBench (Vals AI)Not measured2.7%Only GPT-6 Luna measured
Finance Agent (Vals AI)31.0%49.9%GPT-6 Luna
Tax Agent Bench (Vals AI)5.9%19.9%GPT-6 Luna
Legal Research Bench (Vals AI)10.6%30.3%GPT-6 Luna
Harvey's Legal Agent Benchmark (Vals AI)Not measured4.2%Only GPT-6 Luna measured
Excel Modeling Benchmark (Vals AI)22.7%68.5%GPT-6 Luna
BioMysteryBench (Vals AI)Not measured61.5%Only GPT-6 Luna measured
Terminal-Bench-Science (Vals AI)Not measured4.3%Only GPT-6 Luna measured
Vals Science IndexNot measured28.4%Only GPT-6 Luna measured
APEX-AgentsNot measured44.3%Only GPT-6 Luna measured
BALROG31.2%Not measuredOnly Claude Haiku 4.5 measured
DeepResearch Bench45.5%Not measuredOnly Claude Haiku 4.5 measured
SpireClimbNot measured0.0%Only GPT-6 Luna measured
Vending-Bench 2$459Not measuredOnly Claude Haiku 4.5 measured
Neither model has a result on the other 18 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index35
Reasoning benchmarks for Claude Haiku 4.5 and GPT-6 Luna
BenchmarkClaude Haiku 4.5GPT-6 LunaLeader
GPQA Diamond72.2%Not measuredOnly Claude Haiku 4.5 measured
LiveBench reasoning61.7%81.8%GPT-6 Luna
MysteryMechanism (Vals AI)Not measured19.4%Only GPT-6 Luna measured
MMMU Pro (Vals AI)46.1%Not measuredOnly Claude Haiku 4.5 measured
Humanity's Last Exam (Artificial Analysis run)Not measured38.5%Only GPT-6 Luna measured
GPQA Diamond (Epoch AI run)71.2%90.5%GPT-6 Luna
ARC-AGI47.7%86.7%GPT-6 Luna
ARC-AGI-24.0%59.3%GPT-6 Luna
Chess puzzles8.0%36.0%GPT-6 Luna
Mystery game puzzlesNot measured7.0%Only GPT-6 Luna measured
LMArena Text: hard prompts14211410Claude Haiku 4.5
LMArena Text: expert14431442Claude Haiku 4.5
LMArena Text: hard prompts in English14351410Claude Haiku 4.5
LMArena Vision: diagramsNot measured1245Only GPT-6 Luna measured
LMArena Vision: homeworkNot measured1261Only GPT-6 Luna measured
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index12
Math benchmarks for Claude Haiku 4.5 and GPT-6 Luna
BenchmarkClaude Haiku 4.5GPT-6 LunaLeader
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%98.9%GPT-6 Luna
FrontierMath, tiers 1 to 3Not measured78.9%Only GPT-6 Luna measured
FrontierMath, tier 4Not measured56.1%Only GPT-6 Luna measured
ProofBenchNot measured64.0%Only GPT-6 Luna measured
MATH level 596.4%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text: math13981409GPT-6 Luna
LMArena Text: mathematical work14301427Claude 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 index42
Knowledge benchmarks for Claude Haiku 4.5 and GPT-6 Luna
BenchmarkClaude Haiku 4.5GPT-6 LunaLeader
MMLU Pro78.7%Not measuredOnly Claude Haiku 4.5 measured
LegalBench (Vals AI)81.2%Not measuredOnly Claude Haiku 4.5 measured
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%Not measuredOnly Claude Haiku 4.5 measured
MortgageTax (Vals AI)62.2%Not measuredOnly Claude Haiku 4.5 measured
MedQA (Vals AI)79.6%Not measuredOnly Claude Haiku 4.5 measured
MedCode (Vals AI)32.7%44.7%GPT-6 Luna
SimpleQA Verified13.2%41.4%GPT-6 Luna
LMArena Text: science14061386Claude Haiku 4.5
LMArena Text: medicine and healthcare13941352Claude Haiku 4.5
LMArena Text: legal and government14001400Claude Haiku 4.5
LMArena Text: business and finance14001388Claude Haiku 4.5
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index09
Web design benchmarks for Claude Haiku 4.5 and GPT-6 Luna
BenchmarkClaude Haiku 4.5GPT-6 LunaLeader
Design Arena: websites11221272GPT-6 Luna
Design Arena: UI components11001297GPT-6 Luna
Design Arena: game dev10971259GPT-6 Luna
Design Arena: data viz11241215GPT-6 Luna
Design Arena: 3D10721217GPT-6 Luna
Design Arena: all code categories11151271GPT-6 Luna
Design Arena: SVG10251253GPT-6 Luna
Design Arena: ASCII art11391156GPT-6 Luna
LiveBench design59.9%82.5%GPT-6 Luna
GeneralLike-for-likePublic boards, shown as published, kept out of the index1112
General benchmarks for Claude Haiku 4.5 and GPT-6 Luna
BenchmarkClaude Haiku 4.5GPT-6 LunaLeader
Vals IndexNot measured52.3%Only GPT-6 Luna measured
LiveBench data analysis59.3%73.4%GPT-6 Luna
Public Benefits Bench (Vals AI)54.3%57.6%GPT-6 Luna
SAGE (Vals AI)31.8%48.1%GPT-6 Luna
MedScribe (Vals AI)85.2%83.7%Claude Haiku 4.5
Vals Multimodal Index42.9%Not measuredOnly Claude Haiku 4.5 measured
Long context reasoning (AA-LCR)Not measured83.3%Only GPT-6 Luna measured
DTBench73.6%90.1%GPT-6 Luna
LMCA30.9%44.5%GPT-6 Luna
Furniture assemblyNot measured44.2%Only GPT-6 Luna measured
ExploitBench13.7%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text13971389Claude Haiku 4.5
LMArena Text: instruction following14141408Claude Haiku 4.5
LMArena Text: creative writing13711363Claude Haiku 4.5
LMArena VisionNot measured1216Only GPT-6 Luna measured
LMArena Text: English14141393Claude Haiku 4.5
LMArena Text: non-English13771381GPT-6 Luna
LMArena Text: Chinese14181427GPT-6 Luna
LMArena Text: German13741376GPT-6 Luna
LMArena Text: Japanese13381369GPT-6 Luna
LMArena Text: Korean13461359GPT-6 Luna
LMArena Text: French14111408Claude Haiku 4.5
LMArena Text: Spanish14211391Claude Haiku 4.5
LMArena Text: Russian13811392GPT-6 Luna
LMArena Text: Polish13431383GPT-6 Luna
LMArena Text: multi-turn14091392Claude Haiku 4.5
LMArena Text: longer queries14271408Claude Haiku 4.5
LMArena Text: writing and language13861384Claude Haiku 4.5
LMArena Text: entertainment and media13691364Claude Haiku 4.5
LMArena Vision: EnglishNot measured1204Only GPT-6 Luna measured
LMArena Vision: ChineseNot measured1266Only GPT-6 Luna measured
LMArena Vision: reading textNot measured1225Only GPT-6 Luna measured
LMArena Vision: creative writingNot measured1205Only GPT-6 Luna measured
LMArena Document1420Not measuredOnly Claude Haiku 4.5 measured
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 GPT-6 Luna
BenchmarkClaude Haiku 4.5GPT-6 LunaLeader
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
GPT-6 Luna$0.0003Fits in one request

GPT-6 Luna costs less

Repository review

50K input + 3K output tokens

Claude Haiku 4.5$0.065Fits in one request
GPT-6 Luna$0.0065Fits in one request

GPT-6 Luna costs less

Agent loop

200K input + 10K output tokens

Claude Haiku 4.5$0.250Exceeds the context window
GPT-6 Luna$0.025Fits in one request

GPT-6 Luna 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 GPT-6 Luna
SpecificationAnthropic Claude Haiku 4.5OpenAI GPT-6 Luna
MakerAnthropicOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedOctober 15, 2025September 22, 2026
Context window200K1.05M
Input $/Mtok$1.00$0.10
Output $/Mtok$5.00$0.50
Coding index49.871.4
Independent measurements behind it32
Cost per solved task$0.56Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Haiku 4.5 better than GPT-6 Luna for coding?

Pick GPT-6 Luna for coding: it scores 71.4 on the Vibe Coding Index against 49.8 for Claude Haiku 4.5, though on 2 benchmarks against 3. Pick Claude Haiku 4.5 when what matters is LMArena Text: coding or LMArena Text: software and IT, where it leads.

Which is cheaper, Claude Haiku 4.5 or GPT-6 Luna?

Claude Haiku 4.5 costs $1.00 per million input tokens and $5.00 per million output tokens; GPT-6 Luna costs $0.10 and $0.50. Cost per solved task is known for Claude Haiku 4.5 only.

Which has the bigger context window, Claude Haiku 4.5 or GPT-6 Luna?

GPT-6 Luna, with 1.05M tokens against 200K.

How many benchmarks is the Claude Haiku 4.5 vs GPT-6 Luna comparison based on?

68 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 GPT-6 Luna'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-gpt-6-luna" title="Claude Haiku 4.5 vs GPT-6 Luna, 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-gpt-6-luna">LLMBenchmark.ai, Claude Haiku 4.5 vs GPT-6 Luna</a></p>