BenchLeader

GPT-6 Luna vs Muse Wonder Full

Full profiles: GPT-6 Luna (OpenAI) and Muse Wonder Full (Meta): every benchmark, price and rank.

Updated · Data from 12 sources

As of 16 Nov 2026, Muse Wonder Full is ahead of GPT-6 Luna on quality (61.7 vs 55.1 on the BenchLeader Index). Muse Wonder Full leads in every category we measure both in.

Key facts (as of 16 Nov 2026)

  • GPT-6 Luna scores 55.1 on the BenchLeader Index and Muse Wonder Full scores 61.7 (BenchLeader, 16 Nov 2026).
  • GPT-6 Luna costs $0.200 per 1M tokens blended (list price, 16 Nov 2026).
  • Of the 53 benchmarks both models have, Muse Wonder Full leads 50 (BenchLeader, 16 Nov 2026).
  • On Arena WebDev, GPT-6 Luna is rated 1577 and Muse Wonder Full 1724 (LMArena, as published by 16 Nov 2026).

Which to pick for…

The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.

Use casePickWhyConfidence
CodingMuse Wonder Full70 vs 57 category score; Arena WebDev 1724 vs 1577High
Agents & tool useMuse Wonder Full64 vs 49 category score; Arena Agent 9 vs 1.6High
ReasoningMuse Wonder Full66 vs 56 category score; HLE-Diamond (AA) 48.5% vs 22.2%High
KnowledgeMuse Wonder Full62 vs 45 category score; AA-Omniscience v1.1 30.6 vs -8.3High
Long documentsEither66 vs 67 category score; AA-LCR v1.1 83.3% vs 83.7%Either
Chat quality (human preference)–Only GPT-6 Luna has an Arena rating (62 category score)Not comparable
High volume on a budgetNeither flagshipA smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs–

Key differences

  • Muse Wonder Full (max) leads on quality: 61.7 vs 55.1.
  • Muse Wonder Full (max) is stronger in agents & tools, coding, knowledge, long context, reasoning.

At a glance

SpecGPT-6 LunaMuse Wonder Full
DeveloperOpenAIMeta
Released22 Sep 202612 Oct 2026
Context window (tokens)1,050,0001,000,000
Compared atGPT-6 Luna (max)Muse Wonder Full (max)
Open weightsNoNo
Price in / out / cached input per 1M$0.100 / $0.500 / $0.010–

Category by category

Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.

CategoryGPT-6 Luna (max)Muse Wonder Full (max)Leader
Reasoning55.765.8Muse Wonder Full
Coding57.369.9Muse Wonder Full
Agents & tools48.563.6Muse Wonder Full
Maths63.6–not comparable
Knowledge44.862.3Muse Wonder Full
Human preference62.2–not comparable
Multimodal57.6–not comparable
Long context66.466.6level
Composite44.5–not comparable

On one chart

Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.

2550 avg75ReasoningCodingAgents & toolsKnowledgeLong contextGPT-6 Luna, Reasoning: 55.7GPT-6 Luna, Coding: 57.3GPT-6 Luna, Agents & tools: 48.5GPT-6 Luna, Knowledge: 44.8GPT-6 Luna, Long context: 66.4Muse Wonder Full, Reasoning: 65.8Muse Wonder Full, Coding: 69.9Muse Wonder Full, Agents & tools: 63.6Muse Wonder Full, Knowledge: 62.3Muse Wonder Full, Long context: 66.6

Not drawn, measured for fewer than two of these models: Maths, Instruction following, Multimodal, Human preference.

Model, click to add or removeIndex

Where sources disagree

Across the 53 benchmarks both have, GPT-6 Luna leads 2, Muse Wonder Full leads 50 and 1 is a tie. Every overall index that rates both puts Muse Wonder Full ahead.

Overall indexGPT-6 Luna (max)Muse Wonder Full (max)Leader
BenchLeader Index55.161.7Muse Wonder Full
AA Intelligence Index v5.0.127.950.1Muse Wonder Full
Vals Index52.366.8Muse Wonder Full

Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).

Price, speed and latency

List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.

MeasureGPT-6 Luna (max)Muse Wonder Full (max)
Blended price per 1M tokens$0.200–
Input / output per 1M$0.100 / $0.500– / –
Cached input per 1M$0.010–
Price per task: chat reply$0.0002–
Price per task: summarize a 30-page report$0.0015–
Price per task: code edit$0.0014–
Price per task: agentic coding session$0.0080–
Price per task: structured extraction$0.0003–
Agentic coding session, input mostly cached$0.0040–
Cost per benchmark task (AA Index)$0.152–
Output tokens per task (AA Index)75k88k
Of which reasoning58k55k
Time per task (AA Index)12 min–
Output speed103 tok/s–
Time to first answer73.9 s–
Time to a complete answer, last measured 13 Nov 2026171.6 s–

Each model is compared at its best-ranked reasoning-effort setting. GPT-6 Luna (max) scores 55.1 and takes 74 s to its first answer token; GPT-6 Luna (xhigh) scores 52.0 in 17 s, GPT-6 Luna (high) scores 51.1 in 10 s. Muse Wonder Full (max) scores 61.7. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.

Every benchmark

145 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.

MetricPublisherGPT-6 Luna (max)Muse Wonder Full (max)
BenchLeader IndexBenchLeader55.161.7
Agents & tools scoreBenchLeader48.563.6
Coding scoreBenchLeader57.369.9
Composite scoreBenchLeader44.5–
Human preference scoreBenchLeader62.2–
Knowledge scoreBenchLeader44.862.3
Long context scoreBenchLeader66.466.6
Maths scoreBenchLeader63.6–
Multimodal scoreBenchLeader57.6–
Reasoning scoreBenchLeader55.765.8
Blended price $/MBenchLeader$0.200–
Output speedBenchLeader103 tok/s–
Time to first answerBenchLeader73.9 s–
Context windowBenchLeader1,050,000 tokens1,000,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub90.5%–
Arena Hard PromptsArena (LMArena)1464–
LiveBench 2.0 ReasoningLiveBench81.8%–
LiveBench 1.0 ReasoningLiveBench81.8%–
Humanity's Last Exam (AA)Artificial Analysis38.5%53.6%
HLE-Diamond (AA)Artificial Analysis22.2%48.5%
ARC-AGI-1ARC Prize86.7%–
ARC-AGI-2ARC Prize59.3%–
ARC-AGI-3ARC Prize0.6%–
CritPtArtificial Analysis19.4%32.9%
CritPt v2 hard subset (AA)Artificial Analysis42.5%56.5%
MysteryMechanismVals AI19.4%35.1%
Arena ExpertArena (LMArena)1487–
Chess PuzzlesEpoch AI Benchmarking Hub36.0%–
Mystery Game PuzzlesEpoch AI Benchmarking Hub7.0%–
LMCAEpoch AI Benchmarking Hub44.5%–
DTBenchEpoch AI Benchmarking Hub90.1%–
Coding
SciCodeSciCode54.6%–
FrontierCodeCognition42.4%–
Arena CodingArena (LMArena)1501–
Arena WebDevArena (LMArena)15771724
LiveBench 2.0 CodingLiveBench70.8%–
LiveBench 1.0 CodingLiveBench79.0%–
SciCode (AA)Artificial Analysis54.6%62.6%
IOIVals AI55.6%79.8%
Show all 145 benchmarks
MetricPublisherGPT-6 Luna (max)Muse Wonder Full (max)
Coding
Code MigrationVals AI42.5%61.0%
Code Migration v1.1Vals AI46.7%62.8%
ProgramBenchVals AI0.5%0.5%
SWE-bench MultimodalVals AI37.5%47.3%
Vibe Code Bench 1-100Vals AI–34.0%
Vibe Code Bench v1.1Vals AI81.7%86.0%
SWE Atlas v1.1Scale AI SEAL50.8%†–
SWE Atlas v1.1: Codebase QnAScale AI SEAL50.8%†–
SWE Atlas v1.1: Test WritingScale AI SEAL54.4%†–
SWE Atlas v1.1: RefactoringScale AI SEAL47.1%†–
MirrorCodeEpoch AI Benchmarking Hub26.7%–
ALE-BenchEpoch AI Benchmarking Hub1576.9†–
WeirdML v3WeirdML7.9%†–
Terminal-Bench 4.0 (AA)Artificial Analysis12.6%57.1%
Startrise FrontendStartrise69.3%†–
GameBench 2 OverallDuelLab GameBench 247.5†–
GameBench 2 by reasoning settingDuelLab GameBench 255.9†–
Design Arena WebsiteDesign Arena1268†–
FrontierCode 1.1 (AA)Artificial Analysis41.9%44.9%
FrontierCode 2.0 (AA)Artificial Analysis25.2%37.8%
Agents & tools
Terminal-BenchTerminal-Bench15.2%–
APEX-AgentsMercor44.3%–
Arena AgentArena (LMArena)1.69
LiveBench Long AgenticLiveBench24.7%–
LiveBench BrowserLiveBench70.3%–
LiveBench Agentic CodingLiveBench51.2%–
Terminal-Bench 2.1 (Vals)Vals AI73.0%–
GDPval-AA v2.1, normalised scoreArtificial Analysis46.6%67.8%
GDPval-AA v2.1Artificial Analysis14431857
Analyst Agent (AA)Artificial Analysis43.8%–
CyberBenchVals AI76.3%73.6%
Finance Agent v2Vals AI49.9%59.1%
Finance Agent v2.1Vals AI56.8%67.6%
Harvey's Legal Agent Benchmark v1.1Vals AI4.2%23.3%
Harvey's Legal Agent Benchmark v1Vals AI2.9%21.7%
Legal Research BenchVals AI30.3%53.4%
Robo-benchVals AI–10.4%
SREBenchVals AI2.7%11.8%
Tax Agent BenchVals AI19.9%43.0%
Terminal-Bench 4.0 (Vals)Vals AI13.6%58.1%
Terminal-Bench ScienceVals AI4.3%37.1%
Arena SearchArena (LMArena)1211–
Arena Agent Task CompletionArena (LMArena)-0.411.1
SpireClimbEpoch AI Benchmarking Hub0.0%–
AutomationBenchArtificial Analysis53.2%71.3%
GDP.pdf (AA)Artificial Analysis22.8%32.6%
Harvey LAB-AA v1.1Harvey3.3%13.1%
AA-Briefcase v1.1Artificial Analysis13371729
GDPxGDPx by SemiAnalysis5.1%9.0%
Design Arena AgenticDesign Arena1152†–
Terminal-Bench-Science 0.1 (AA)Artificial Analysis8.6%37.1%
CWE-Bench (AA)Artificial Analysis56.7%–
DeepSec-Bench (AA)Artificial Analysis23.5%–
CyberGym end-to-end (AA)Artificial Analysis77.9%–
MKA (AA)Artificial Analysis36.8%–
FACTS SearchGoogle86.8%†–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub79.0%–
FrontierMath Tier 4Epoch AI Benchmarking Hub56.1%–
OTIS Mock AIMEEpoch AI Benchmarking Hub98.9%–
ProofBenchVals AI64.0%†–
LiveBench MathematicsLiveBench89.1%–
Arena MathsArena (LMArena)1449–
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub41.4%–
LiveBench 2.0 Data AnalysisLiveBench73.4%–
LiveBench ResearchLiveBench48.5%–
LiveBench 1.0 Data AnalysisLiveBench73.4%–
AA-Omniscience v1.1Artificial Analysis-8.330.6
LegalBenchVals AI–87.4%
PRBench LegalScale AI SEAL42.9%†–
BioMysteryBenchVals AI61.5%73.3%
ClaimBenchVals AI99.2%–
Excel Modeling BenchmarkVals AI68.5%71.9%
Excel Modeling Benchmark v1.1Vals AI70.0%75.0%
MedCodeVals AI44.7%49.9%
MedScribeVals AI83.7%89.3%
Public Benefits Bench v1.1Vals AI57.6%73.8%
Access to Justice BenchmarkVals AI–74.7%
Financial Coaching BenchVals AI65.2%75.0%
Immigration BenchVals AI62.5%71.2%
GDP.pdfEpoch AI Benchmarking Hub23.0%–
AA-Omniscience v1.1: accuracyArtificial Analysis39.6%41.0%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis20.6%82.4%
HealthBench Professional (AA)OpenAI61.9%–
FACTS ParametricGoogle57.0%†–
Instruction following
LiveBench LanguageLiveBench73.8%–
LiveBench Instruction FollowingLiveBench55.9%–
Arena Instruction FollowingArena (LMArena)1436–
Human preference
Arena TextArena (LMArena)1441–
Arena Creative WritingArena (LMArena)1408–
Arena Multi-turnArena (LMArena)1441–
Arena Longer QueriesArena (LMArena)1449–
Multimodal
Arena VisionArena (LMArena)1211–
LiveBench DesignLiveBench76.1%–
MMMU-ProArtificial Analysis79.7%–
SAGEVals AI83.4%–
Humanity's Sixth SenseScale AI SEAL21.0%–
Blueprint-Bench 2Epoch AI Benchmarking Hub31.2%†–
Furniture AssemblyEpoch AI Benchmarking Hub44.2%–
VIALS-AAHandshake AI27.3%–
Code2Video-AAArtificial Analysis1030–
AA-3DArtificial Analysis1000–
FACTS MultimodalGoogle38.7%†–
Long context
AA-LCR v1.1Artificial Analysis83.3%83.7%
MLCRArtificial Analysis26.1%22.2%
FACTS GroundingGoogle76.7%†–
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub156.4†–
LiveBench 2.0LiveBench60.4%–
LiveBench 1.0LiveBench72.0%–
AA Intelligence Index v5.0.1Artificial Analysis27.950.1
AA Intelligence Index v4.3.2Artificial Analysis38.155.8
AA Progress Index v1Artificial Analysis317.1343.2
Vals IndexVals AI52.366.8
Vals Finance IndexVals AI53.0%64.5%
Vals RSI IndexVals AI–24.4%
Vals Science IndexVals AI28.4%48.5%
Vals Router IndexVals AI52.3%†66.8%†
Vals Legal IndexVals AI62.2%77.9%
AA Cyber IndexArtificial Analysis52.7–
Safety & honesty
FORTRESSScale AI SEAL10.8%†–
DistressBenchScale AI SEAL66.7%†–

Data as of 2026-11-16. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261111-7b598bb13de4 (https://benchmarks.duellab.org/releases/gb2-20261111-7b598bb13de4/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.

What changed

  • GPT-6 Luna (max): BenchLeader Index 56.6 → 55.1.
  • GPT-6 Luna (max): 8 new results (LiveBench 2.0, LiveBench Long Agentic, LiveBench 2.0 Reasoning…).
  • Muse Wonder Full (max): BenchLeader Index 62.6 → 61.7.
  • GPT-6 Luna (max): 1 score revision.
  • GPT-6 Luna (max): 1 score revision.
  • GPT-6 Luna (max): 1 score revision.
  • Muse Wonder Full (max): 1 score revision.
  • Muse Wonder Full (max): 1 score revision.
  • GPT-6 Luna (max): 1 score revision.
  • Muse Wonder Full (max): 1 new result (Arena Agent).

Rankings: Best LLM overall · Best LLM for coding · Best LLM for agents · Best cheap LLMs

GPT-6 Luna vs Muse Wonder Full: questions

Is Muse Wonder Full better than GPT-6 Luna?
Muse Wonder Full (max) leads on quality: 61.7 vs 55.1. The BenchLeader Index combines every independent quality benchmark; Muse Wonder Full (max) is ahead overall as of 16 Nov 2026, but check the category scores for your use.
Is GPT-6 Luna or Muse Wonder Full better for coding?
Muse Wonder Full scores higher in coding (70 vs 57 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1577 for GPT-6 Luna against 1724 for Muse Wonder Full.
Is GPT-6 Luna or Muse Wonder Full better for agents and tool use?
Muse Wonder Full scores higher in agentic tasks (64 vs 49 on the category index, where 50 is average). On Arena Agent, the top shared agents & tools benchmark, it is 1.6 for GPT-6 Luna against 9 for Muse Wonder Full.
Which is better for long documents?
They are level on long-context benchmarks (66 vs 67). Both take about 1.1M tokens: GPT-6 Luna 1,050,000, Muse Wonder Full 1,000,000.
Do independent benchmarks agree on GPT-6 Luna vs Muse Wonder Full?
Across the 53 benchmarks both have, GPT-6 Luna leads 2, Muse Wonder Full leads 50 and 1 is a tie. Every overall index that rates both puts Muse Wonder Full ahead.
More questions (1)
When was Muse Wonder Full released?
Muse Wonder Full was released on 12 Oct 2026.