Atlas

Compare Models

Claude Opus 5.5 vs Muse Wonder Full

Claude Opus 5.5 leads by 3.1 capability points (≈95% interval +0.5 to +5.7): a clear lead over Muse Wonder Full · P(higher) ≈ 99%

Wins 35 of 75 shared benchmarks (32 lost, 8 tied)

Capability vs. relative cost
Claude Opus 5.5Muse Wonder FullClosed weightsOpen weights

Each line runs through one model’s priced reasoning settings, cheapest to most expensive; grey points are other models’ priced settings in the same range. Results whose reasoning effort the source didn’t report are left out wherever a model has named effort levels. Capability and relative cost are the published estimates (relative cost is cost per task as a multiple of GPT-5 (high)); hover a setting, or use the arrow keys, to set it beside the other model’s same setting.

Claude Opus 5.5vsMuse Wonder Fullcapability vs. relative costData Nov 15, 2026Village LLM Atlasatlas.village.dev

Benchmark wins35 – 32 · 75 shared, 8 tied

Comparing matching setups only (9 benchmarks excluded) · suites counted once
← Claude Opus 5.5Muse Wonder Full →

Claude Opus 5.5vsMuse Wonder Fullwins by categoryData Nov 15, 2026Data: Vals AI, Artificial Analysis, Arena and 13 othersVillage LLM Atlasatlas.village.dev

Margins

Each benchmark scaled 0–100% (its declared range, else the field’s range); Δ is Muse Wonder Full minus Claude Opus 5.5.

Harvey's Legal Agent Benchmark - Corporate GovernanceLegal0.040.0+40.0
Harvey's Legal Agent Benchmark - Real EstateLegal0.040.0+40.0
Harvey's Legal Agent Benchmark - Trusts Estates Private ClientLegal0.040.0+40.0
LisanBench Difficulty-WeightedGames59639337+36.1
LisanBench Path LengthGames2402932190+25.4
Terminal-Bench-Science 0.1Science61.937.1−24.8
SWE-bench Multimodal (Vals v1, 480 Tasks)Code70.247.3−22.9
VulcanBench Frontier v4 (functional pass@1)Code73.995.7+21.7
Harvey's Legal Agent Benchmark - Antitrust CompetitionLegal0.020.0+20.0
Harvey's Legal Agent Benchmark - Arbitration International Dispute ResolutionLegal0.020.0+20.0
Harvey's Legal Agent Benchmark - Banking FinanceLegal0.020.0+20.0
Harvey's Legal Agent Benchmark - Bankruptcy RestructuringLegal0.020.0+20.0
Harvey's Legal Agent Benchmark - Capital MarketsLegal0.020.0+20.0
Harvey's Legal Agent Benchmark - Corporate M&ALegal0.020.0+20.0
Harvey's Legal Agent Benchmark - Data Privacy CybersecurityLegal0.020.0+20.0
Harvey's Legal Agent Benchmark - Energy Natural ResourcesLegal20.040.0+20.0
Harvey's Legal Agent Benchmark - Funds Asset ManagementLegal0.020.0+20.0
Harvey's Legal Agent Benchmark - ImmigrationLegal0.020.0+20.0
Harvey's Legal Agent Benchmark - InsuranceLegal0.020.0+20.0
Harvey's Legal Agent Benchmark - Intellectual PropertyLegal0.020.0+20.0
Harvey's Legal Agent Benchmark - Structured Finance SecuritizationLegal0.020.0+20.0
LMArena Agent Arena Net Improvement (Steering Burden)Agents19.59.0−19.9
Harvey HLAB — Criteria Pass RateLegal75.893.5+17.8
RiemannBench (November 2026 rescoring)Math80.063.2−16.8
HLAB-Vals-1.1Legal9.223.3+14.2
Vals RSI Index v1.1 (four tasks)Agents37.324.4−12.9
LMArena Agent Arena Praise vs ComplaintAgents40.315.4−12.4
LMArena Code Arena WebDevCode18141723−11.9
ProgramBench - almost solved rollout percentageCode70.559.0−11.5
SWE-Marathon - release-reported version unspecifiedCode46.357.5+11.2
FrontierCode 2.0 (Artificial Analysis)Code46.437.8−8.7
AA-Omniscience IndexIndexes46.430.1−8.1
FrontierCode 1.1 Main (Artificial Analysis)Code52.244.9−7.3
AgenticRL-Bench (Verifiable)Agents14.07.0−7.0
SWE-Marathon v1.1Code46.353.1+6.9
CritPt v2 (agentic, avg@5)Science81.775.1−6.6
Humanity's Last Exam DiamondGeneral QA54.648.5−6.1
ProofBench v1.1Math100.094.0−6.0
Medical Long Context Reasoning (MLCR-AA, October 2026 methodology)Health & Medicine27.822.2−5.6
DeepSWE v1.1Code74.279.0+4.8
LMArena Agent Arena Confirmed SuccessAgents20.711.1−4.8
LMArena Agent Arena Steering BurdenAgents18.69.6−4.5
SciCode 1.0.1 (Artificial Analysis)Code66.962.6−4.3
AutomationBench-AA - release-reported strict pass rateAgents41.245.4+4.2
Robo-benchAgents14.610.4−4.2
Excel Modeling BenchmarkFinance & Accounting75.971.9−4.0
MazeBench ASCII with PythonGames13.017.0+4.0
AA-Briefcase v1.1 EloAgents18011729−3.9
Humanity's Last Exam (Text-Only)General QA57.553.6−3.9
LMArena Agent Arena Bash ReliabilityAgents15.18.3−3.4
OSWorld 2.1 full - reported partial reward, step limit unspecifiedAgents81.878.4−3.4
GDPxProfessional Work12.09.0−3.0
GDP.pdfProfessional Work30.633.2+2.6
MASKSafety89.487.3−2.1
MedScribeHealth & Medicine91.489.3−2.1
Artificial Analysis Coding Agent Index v1.5Indexes66.068.0+2.0
Financial Coaching BenchFinance & Accounting76.275.0−1.2
CritPt (avg@5)Science31.732.9+1.1
AA-LCR v1.1Search84.783.7−1.0
Immigration BenchLegal72.171.2−0.9
Access to Justice BenchmarkLegal73.874.7+0.9
Excel Modeling Benchmark v1.1Finance & Accounting75.875.0−0.8
GDPval-AA v2.1Professional Work18661857−0.4
LMArena Agent Arena Tool HallucinationAgents0.70.0−0.3
Bug Hunt BenchCode39.740.0+0.3
MedCodeHealth & Medicine49.849.9+0.1
JobBench - release-reported mean task rewardProfessional Work75.475.3−0.1
Harvey's Legal Agent Benchmark - Emerging Companies Venture CapitalLegal0.00.00.0
Harvey's Legal Agent Benchmark - Employment LaborLegal0.00.00.0
Harvey's Legal Agent Benchmark - Environmental ESGLegal0.00.00.0
Harvey's Legal Agent Benchmark - Healthcare Life SciencesLegal20.020.00.0
Harvey's Legal Agent Benchmark - International Trade SanctionsLegal0.00.00.0
Harvey's Legal Agent Benchmark - Litigation Dispute ResolutionLegal0.00.00.0
Harvey's Legal Agent Benchmark - TaxLegal0.00.00.0
Harvey's Legal Agent Benchmark - White Collar Defense InvestigationsLegal0.00.00.0

Claude Opus 5.5vsMuse Wonder Fullnormalised score marginsData Nov 15, 2026Data: Vals AI, Artificial Analysis, Arena and 13 othersVillage LLM Atlasatlas.village.dev

Win counts use each benchmark’s declared score direction. Represented suite slices and the derived Capability score are excluded from headline totals. Missing or incompatible setups are excluded, never counted as losses.
Loading Atlas data…