Enter opens the highlighted result. Esc closes.

Claude Haiku 4.5 vs GPT-5.6 Luna

GPT-5.6 Luna leads Claude Haiku 4.5 on coding, 58.0 to 35.6 on the Vibe Coding Index, and GPT-5.6 Luna costs 4.2x less per output token ($1.20 vs $5.00 per million). Updated October 22, 2026; 84 benchmarks have a result for both.

Replace Claude Haiku 4.5 Replace GPT-5.6 Luna
Claude Haiku 4.5Anthropic
Coding
35.6
Overall
41.0
Output $/M
$5.00
1
GPT-5.6 LunaOpenAI
Coding
58.0
Overall
61.6
Output $/M
$1.20
82
vs boards won of 84 shared, 1 tied

Claude Haiku 4.5 or GPT-5.6 Luna: which to pick

Pick GPT-5.6 Luna for coding: it scores 58.0 on the Vibe Coding Index against 35.6 for Claude Haiku 4.5.

Pick Claude Haiku 4.5 for work measured by MedScribe (Vals AI), where it leads.

Model AClaude Haiku 4.5Anthropic35.6/1004 independent benchmarks$0.56 per solved taskModel BGPT-5.6 LunaOpenAI58.0/1006 independent benchmarks$0.04 per solved task
Shared results
84
Claude Haiku 4.5 only
14
GPT-5.6 Luna only
36
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, GPT-5.6 Luna 58.0 from 6 benchmarks.
Widest category
Coding, 25.4 points apart on average over 13 shared benchmarks.
Widest single gap
Vibe Code Bench (Vals AI): Claude Haiku 4.5 11.4% against GPT-5.6 Luna 77.1%, 65.7 points apart on a 0 to 100 scale.
Output price
Claude Haiku 4.5 $5.00 against GPT-5.6 Luna $1.20 per million output tokens, 4.2x apart.
Context window
Claude Haiku 4.5 takes 200K tokens, GPT-5.6 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-5.6 LunaTies
Coding0121 tie
Intelligence02
Agentic work010
Reasoning010
Math03
Knowledge011
Web design09
General125
All shared boards1821 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index012
Coding benchmarks for Claude Haiku 4.5 and GPT-5.6 Luna
BenchmarkClaude Haiku 4.5GPT-5.6 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%73.6%GPT-5.6 Luna
LMArena WebDev13301518GPT-5.6 Luna
AA Coding Index43.971.4GPT-5.6 Luna
LiveCodeBench (Vals AI)41.2%Not measuredOnly Claude Haiku 4.5 measured
SWE-bench Verified (Vals AI)66.6%93.0%GPT-5.6 Luna
Terminal-Bench 4 (Vals AI)Not measured11.6%Only GPT-5.6 Luna measured
Vibe Code Bench (Vals AI)11.4%77.1%GPT-5.6 Luna
Code migration (Vals AI)7.5%44.5%GPT-5.6 Luna
ProgramBench (Vals AI)0.0%0.0%Tie
IOI (Vals AI)Not measured61.8%Only GPT-5.6 Luna measured
Terminal-Bench 2.1 (Vals AI)43.8%79.0%GPT-5.6 Luna
Vibe Code Bench 1-100 (Vals AI)Not measured22.6%Only GPT-5.6 Luna measured
SkillsBench (Vals AI)Not measured60.5%Only GPT-5.6 Luna measured
CyberBench (Vals AI)Not measured73.6%Only GPT-5.6 Luna measured
SciCodeNot measured53.6%Only GPT-5.6 Luna measured
Terminal-Bench35.5%Not measuredOnly Claude Haiku 4.5 measured
FrontierCodeNot measured39.8%Only GPT-5.6 Luna measured
WeirdML45.4%60.9%GPT-5.6 Luna
ALE-BenchNot measured1667.4Only GPT-5.6 Luna measured
LMArena Text: coding14541466GPT-5.6 Luna
LMArena Text: software and IT14391463GPT-5.6 Luna
LMArena WebDev: React13261508GPT-5.6 Luna
LMArena WebDev: HTML13181520GPT-5.6 Luna
LMArena WebDev: from an imageNot measured1517Only GPT-5.6 Luna measured
SciCodeNot measured6.2%Only GPT-5.6 Luna measured
Neither model has a result on the other 16 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Claude Haiku 4.5 and GPT-5.6 Luna
BenchmarkClaude Haiku 4.5GPT-5.6 LunaLeader
AA Intelligence Index16.937.3GPT-5.6 Luna
Epoch Capabilities Index142.2156.5GPT-5.6 Luna
Agentic workLike-for-likePublic boards, shown as published, kept out of the index010
Agentic work benchmarks for Claude Haiku 4.5 and GPT-5.6 Luna
BenchmarkClaude Haiku 4.5GPT-5.6 LunaLeader
AA Agentic Index8.042.1GPT-5.6 Luna
LiveBench research42.2%51.0%GPT-5.6 Luna
LiveBench browser40.0%68.0%GPT-5.6 Luna
LiveBench long agentic11.1%30.4%GPT-5.6 Luna
SREBench (Vals AI)Not measured1.5%Only GPT-5.6 Luna measured
Finance Agent (Vals AI)31.0%55.0%GPT-5.6 Luna
Tax Agent Bench (Vals AI)5.9%24.8%GPT-5.6 Luna
Legal Research Bench (Vals AI)10.6%36.5%GPT-5.6 Luna
Excel Modeling Benchmark (Vals AI)22.7%67.1%GPT-5.6 Luna
BioMysteryBench (Vals AI)Not measured61.5%Only GPT-5.6 Luna measured
Terminal-Bench-Science (Vals AI)Not measured0.0%Only GPT-5.6 Luna measured
Vals Science IndexNot measured25.3%Only GPT-5.6 Luna measured
APEX-AgentsNot measured43.0%Only GPT-5.6 Luna measured
BALROG31.2%45.6%GPT-5.6 Luna
DeepResearch Bench45.5%Not measuredOnly Claude Haiku 4.5 measured
Vending-Bench 2$459$4,095GPT-5.6 Luna
Berkeley Function Calling Leaderboard (BFCL)68.7%Not measuredOnly Claude Haiku 4.5 measured
MCP Atlas40.2%Not measuredOnly Claude Haiku 4.5 measured
Neither model has a result on the other 24 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index010
Reasoning benchmarks for Claude Haiku 4.5 and GPT-5.6 Luna
BenchmarkClaude Haiku 4.5GPT-5.6 LunaLeader
GPQA Diamond72.2%91.7%GPT-5.6 Luna
LiveBench reasoning61.7%85.6%GPT-5.6 Luna
MysteryMechanism (Vals AI)Not measured14.4%Only GPT-5.6 Luna measured
MMMU Pro (Vals AI)46.1%85.0%GPT-5.6 Luna
GPQA Diamond (Artificial Analysis run)Not measured91.1%Only GPT-5.6 Luna measured
Humanity's Last Exam (Artificial Analysis run)Not measured39.5%Only GPT-5.6 Luna measured
GPQA Diamond (Epoch AI run)71.2%91.6%GPT-5.6 Luna
ARC-AGI47.7%88.0%GPT-5.6 Luna
ARC-AGI-24.0%59.5%GPT-5.6 Luna
SimpleBenchNot measured46.8%Only GPT-5.6 Luna measured
Chess puzzles8.0%43.0%GPT-5.6 Luna
Mystery game puzzlesNot measured21.0%Only GPT-5.6 Luna measured
LMArena Text: hard prompts14211451GPT-5.6 Luna
LMArena Text: expert14431478GPT-5.6 Luna
LMArena Text: hard prompts in English14351460GPT-5.6 Luna
LMArena Vision: diagramsNot measured1273Only GPT-5.6 Luna measured
LMArena Vision: homeworkNot measured1282Only GPT-5.6 Luna measured
Kagi LLM BenchmarkNot measured49.1%Only GPT-5.6 Luna measured
Neither model has a result on the other 5 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index03
Math benchmarks for Claude Haiku 4.5 and GPT-5.6 Luna
BenchmarkClaude Haiku 4.5GPT-5.6 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%98.3%GPT-5.6 Luna
FrontierMath, tiers 1 to 3Not measured82.1%Only GPT-5.6 Luna measured
FrontierMath, tier 4Not measured61.0%Only GPT-5.6 Luna measured
ProofBenchNot measured60.0%Only GPT-5.6 Luna measured
MATH level 596.4%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text: math13981459GPT-5.6 Luna
LMArena Text: mathematical work14301470GPT-5.6 Luna
Neither model has a result on the other 5 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index011
Knowledge benchmarks for Claude Haiku 4.5 and GPT-5.6 Luna
BenchmarkClaude Haiku 4.5GPT-5.6 LunaLeader
MMLU Pro78.7%86.0%GPT-5.6 Luna
LegalBench (Vals AI)81.2%84.0%GPT-5.6 Luna
CaseLaw (Vals AI)56.5%Not measuredOnly Claude Haiku 4.5 measured
CorpFin (Vals AI)60.6%64.2%GPT-5.6 Luna
TaxEval (Vals AI)67.5%76.2%GPT-5.6 Luna
MortgageTax (Vals AI)62.2%67.3%GPT-5.6 Luna
MedQA (Vals AI)79.6%Not measuredOnly Claude Haiku 4.5 measured
MedCode (Vals AI)32.7%42.4%GPT-5.6 Luna
SimpleQA Verified13.2%41.0%GPT-5.6 Luna
LMArena Text: science14061433GPT-5.6 Luna
LMArena Text: medicine and healthcare13941399GPT-5.6 Luna
LMArena Text: legal and government14001446GPT-5.6 Luna
LMArena Text: business and finance14001439GPT-5.6 Luna
FACTS Benchmark SuiteNot measured35.0%Only GPT-5.6 Luna measured
Neither model has a result on the other 6 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-5.6 Luna
BenchmarkClaude Haiku 4.5GPT-5.6 LunaLeader
Design Arena: websites11221255GPT-5.6 Luna
Design Arena: UI components10971248GPT-5.6 Luna
Design Arena: game dev10961195GPT-5.6 Luna
Design Arena: data viz11241212GPT-5.6 Luna
Design Arena: 3D10711121GPT-5.6 Luna
Design Arena: all code categories11141230GPT-5.6 Luna
Design Arena: SVG10251193GPT-5.6 Luna
Design Arena: ASCII art11401142GPT-5.6 Luna
LiveBench design59.9%76.0%GPT-5.6 Luna
GeneralLike-for-likePublic boards, shown as published, kept out of the index125
General benchmarks for Claude Haiku 4.5 and GPT-5.6 Luna
BenchmarkClaude Haiku 4.5GPT-5.6 LunaLeader
LiveBench data analysis59.3%78.0%GPT-5.6 Luna
Public Benefits Bench (Vals AI)54.3%61.2%GPT-5.6 Luna
SAGE (Vals AI)31.8%44.2%GPT-5.6 Luna
MedScribe (Vals AI)85.2%84.4%Claude Haiku 4.5
Vals Multimodal Index42.9%69.1%GPT-5.6 Luna
Long context reasoning (AA-LCR)Not measured83.7%Only GPT-5.6 Luna measured
DTBench73.6%89.1%GPT-5.6 Luna
LMCA30.9%48.5%GPT-5.6 Luna
Surface Evolver BenchNot measured61.9%Only GPT-5.6 Luna measured
Furniture assemblyNot measured42.5%Only GPT-5.6 Luna measured
ExploitBench13.7%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text13971431GPT-5.6 Luna
LMArena Text: instruction following14141437GPT-5.6 Luna
LMArena Text: creative writing13711396GPT-5.6 Luna
LMArena VisionNot measured1257Only GPT-5.6 Luna measured
LMArena Text: English14141441GPT-5.6 Luna
LMArena Text: non-English13771417GPT-5.6 Luna
LMArena Text: Chinese14181470GPT-5.6 Luna
LMArena Text: German13741455GPT-5.6 Luna
LMArena Text: Japanese13381415GPT-5.6 Luna
LMArena Text: Korean13461415GPT-5.6 Luna
LMArena Text: French14111458GPT-5.6 Luna
LMArena Text: Spanish14211446GPT-5.6 Luna
LMArena Text: Russian13811427GPT-5.6 Luna
LMArena Text: Polish13431405GPT-5.6 Luna
LMArena Text: multi-turn14091434GPT-5.6 Luna
LMArena Text: longer queries14271436GPT-5.6 Luna
LMArena Text: writing and language13861419GPT-5.6 Luna
LMArena Text: entertainment and media13691402GPT-5.6 Luna
LMArena Vision: EnglishNot measured1263Only GPT-5.6 Luna measured
LMArena Vision: ChineseNot measured1294Only GPT-5.6 Luna measured
LMArena Vision: reading textNot measured1264Only GPT-5.6 Luna measured
LMArena Vision: humorNot measured1190Only GPT-5.6 Luna measured
LMArena Vision: creative writingNot measured1257Only GPT-5.6 Luna measured
LMArena Document14201457GPT-5.6 Luna
MultiChallenge50.5%Not measuredOnly Claude Haiku 4.5 measured
EQ-Bench 410641156GPT-5.6 Luna
Neither model has a result on the other 11 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-5.6 Luna
BenchmarkClaude Haiku 4.5GPT-5.6 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-5.6 Luna$0.0008Fits in one request

GPT-5.6 Luna costs less

Repository review

50K input + 3K output tokens

Claude Haiku 4.5$0.065Fits in one request
GPT-5.6 Luna$0.014Fits in one request

GPT-5.6 Luna costs less

Agent loop

200K input + 10K output tokens

Claude Haiku 4.5$0.250Exceeds the context window
GPT-5.6 Luna$0.052Fits in one request

GPT-5.6 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-5.6 Luna
SpecificationAnthropic Claude Haiku 4.5OpenAI GPT-5.6 Luna
MakerAnthropicOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedOctober 15, 2025July 9, 2026
Context window200K1.05M
Input $/Mtok$1.00$0.20
Output $/Mtok$5.00$1.20
Coding index35.658.0
Independent measurements behind it46
Cost per solved task$0.56$0.04
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Haiku 4.5 better than GPT-5.6 Luna for coding?

Pick GPT-5.6 Luna for coding: it scores 58.0 on the Vibe Coding Index against 35.6 for Claude Haiku 4.5. Pick Claude Haiku 4.5 for work measured by MedScribe (Vals AI), where it leads.

Which is cheaper, Claude Haiku 4.5 or GPT-5.6 Luna?

Claude Haiku 4.5 costs $1.00 per million input tokens and $5.00 per million output tokens; GPT-5.6 Luna costs $0.20 and $1.20. Per solved SWE-bench Verified task, Claude Haiku 4.5 costs $0.56 and GPT-5.6 Luna $0.04.

Which has the bigger context window, Claude Haiku 4.5 or GPT-5.6 Luna?

GPT-5.6 Luna, with 1.05M tokens against 200K.

How many benchmarks is the Claude Haiku 4.5 vs GPT-5.6 Luna comparison based on?

84 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 GPT-5.6 Luna's on 6. 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-5-6-luna" title="Claude Haiku 4.5 vs GPT-5.6 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-5-6-luna">LLMBenchmark.ai, Claude Haiku 4.5 vs GPT-5.6 Luna</a></p>