Atlas

Compare Models

Claude Opus 5.5 vs Muse Wonder

Claude Opus 5.5 leads by 4.2 capability points (≈95% interval +1.7 to +6.7): a clear lead over Muse Wonder · P(higher) ≈ 100%

Wins 132 of 201 shared benchmarks (54 lost, 15 tied)

Capability vs. relative cost
Claude Opus 5.5Muse WonderClosed 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 Wondercapability vs. relative costData Nov 15, 2026Village LLM Atlasatlas.village.dev

Benchmark wins132 – 54 · 201 shared, 15 tied

Comparing matching setups only (13 benchmarks excluded) · suites counted once
← Claude Opus 5.5Muse Wonder →

Claude Opus 5.5vsMuse Wonderwins by categoryData Nov 15, 2026Data: Vals AI, Artificial Analysis, Mercor and 58 othersVillage LLM Atlasatlas.village.dev

Margins

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

CheatBenchSafety7.273.1−65.9
VoxelBench Text RatingGames26131870−52.9
BioSecBench-Refusal V1 Clean RerunsSafety3.855.3+51.5
HoneyBench v0.2 (hack rate)Safety31.681.0−49.4
Code2Video-AA EloCode1536997−43.7
DeepResearch Bench II (Mercor 130-task set)Search53.310.8−42.5
EBR-bench v4 (card ban, single agent)Games71.431.4−40.0
Harvey's Legal Agent Benchmark - Litigation Dispute ResolutionLegal0.040.0+40.0
FrontierML ($200 wallet)Agents58.819.3−39.6
FrontierCS 2Code58.322.9−35.4
AA-PersonalityBench Transparency indexChat & Writing90.556.2−34.6
AA-PersonalityBench Slop indexChat & Writing20.054.3+34.6
LMArena Agent Arena Net Improvement (Steering Burden)Agents19.51.8−33.5
Web Clone BenchCode34.23.7−30.5
VCT-Refusal (CAIS)Safety90.460.2−30.2
Furniture Assembly BenchmarkMultimodal83.354.2−29.2
RWE-benchAgents29.00.0−29.0
OpenWorldEngineer (Mean@8)Code41.612.7−28.9
Terminal-Bench-Science 0.1Science49.021.9−27.1
sudo L7Code41.715.6−26.1
RuneBenchGames6.65.0−25.3
LisanBench Difficulty-WeightedGames59638303+25.1
SWE-bench Multimodal (Vals v1, 480 Tasks)Code70.245.6−24.6
Decision-Bench v1.1Professional Work59.134.6−24.6
FrontierMath Tier 4 (v2) - PrivateMath95.070.7−24.3
FrontierCode 2.0 - Pass RateCode51.828.8−23.0
HANDBOOK.md Agents v1.1Professional Work52.329.5−22.8
HardGeoBench <=100miMultimodal61.338.8−22.5
FrontierMemory v1.1Agents73.351.1−22.2
FrontierCode 2.0 - ScoreCode47.325.3−22.0
EnigmaEvalGeneral QA57.836.1−21.7
LMArena Code Arena WebDevCode18141649−21.7
HardGeoBench Avg DistanceMultimodal6691369−21.6
LMArena Agent Arena Praise vs ComplaintAgents40.3-1.8−21.1
RiemannBench (November 2026 rescoring)Math80.059.2−20.8
HiL-Bench (Human-in-Loop Benchmark)Agents59.079.7+20.7
DAYJOB: Data ScienceProfessional Work37.316.7−20.6
ProgramBench - almost solved rollout percentageCode70.550.0−20.5
Harvey's Legal Agent Benchmark - Antitrust CompetitionLegal0.020.0+20.0
Harvey's Legal Agent Benchmark - Banking FinanceLegal0.020.0+20.0
Harvey's Legal Agent Benchmark - Capital MarketsLegal0.020.0+20.0
Harvey's Legal Agent Benchmark - Corporate GovernanceLegal0.020.0+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 - Funds Asset ManagementLegal0.020.0+20.0
Harvey's Legal Agent Benchmark - Intellectual PropertyLegal0.020.0+20.0
Harvey's Legal Agent Benchmark - Real EstateLegal0.020.0+20.0
Harvey's Legal Agent Benchmark - Trusts Estates Private ClientLegal0.020.0+20.0
Mystery Game PuzzlesGames71.051.0−20.0
TaxCalcBench TY25Finance & Accounting42.022.0−20.0
Visa Agentic Commerce BenchmarkAgents62.282.2+20.0
ChessBench CoherenceGames80.1100.0+19.9
LLM Creative Story WritingChat & Writing3.72.0−19.8
Machiavelli Deception (CAIS)Safety77.583.6−18.4
Terminal-Bench 4.0 (Artificial Analysis)Code56.638.4−18.2
ChessBench EloGames13491046−18.0
SnorkelManufacturingProfessional Work10.427.8+17.4
Harvey HLAB — Criteria Pass RateLegal75.892.7+17.0
GameBench 2Games94.877.8−17.0
MineBench — Bradley-Terry RatingGames21341868−16.1
ProofBench v1.1Math100.084.0−16.0
GBENCH One-shot Coding GScoreGames73.958.1−15.8
Humanity's Last Exam DiamondGeneral QA54.639.0−15.6
AA-PersonalityBench Warmth indexChat & Writing84.8100+15.4
HardGeoBench Country AccuracyMultimodal67.552.5−15.0
HardGeoBench <=10miMultimodal42.527.5−15.0
CrossSearch (pass^3)Search57.042.0−15.0
HLAB-Vals-1.1Legal9.223.8+14.6
Real-SWE 1.1Code56.842.4−14.4
Conceptual Reasoning IndexIndexes77.967.7−13.9
Eval Connections One-Shot with TrapsGames86.073.0−13.0
APEX-SWECode67.654.6−13.0
EnterpriseBench: CoreCraftProfessional Work74.461.5−12.9
Humanity's Last Exam RMS Calibration Error (CAIS)General QA13.826.7−12.9
SWE Atlas v1.1 - OverallCode77.464.8−12.6
ACCoRDGeneral QA88.476.2−12.3
LisanBench Path LengthGames2402927973+12.3
Harvey LAB (Mercor run, undisclosed ~213-task cohort)Legal10.823.0+12.2
DAXBench v2Code95.784.0−11.7
TextQuests Average Cumulative HarmSafety24.220.8+11.7
AA-PersonalityBench Organization indexChat & Writing79.190.5+11.5
DAYJOB: LawLegal25.136.6+11.5
SciCode (main problems)Science27.315.8−11.5
LMCAGeneral QA68.256.8−11.4
Professional Reasoning Benchmark - LegalLegal47.658.4+10.8
DeepFinanceFinance & Accounting54.844.2−10.6
CritPt v2 (agentic, avg@5)Science81.771.1−10.6
AA-Omniscience IndexIndexes46.425.5−10.5
DistressBenchSafety75.685.9+10.3
SpeciEval (Pooled English Runs)Safety87.297.5+10.3
ChessBench AccuracyGames79.370.2−9.8
TextQuests Game ProgressGames57.347.6−9.7
AA-PersonalityBench Conviction indexChat & Writing69.579.1+9.6
Bug Hunt BenchCode39.730.2−9.5
APEX-1 (Mercor, mean score)Professional Work65.875.1+9.3
Toloka Arena (v3)Agents75.065.7−9.3
OSWorld 2.1 full - reported partial reward, step limit unspecifiedAgents81.872.6−9.2
FrontierMath Tiers 1-3 (v2) - PrivateMath91.282.1−9.1
Excel Modeling BenchmarkFinance & Accounting75.967.1−8.9
VIALSMultimodal40.231.5−8.7
LiveBench 2.0Agents86.578.1−8.4
LMArena Agent Arena Steering BurdenAgents18.62.6−8.0
MMMU-Pro Extended (Mercor held-out)Multimodal51.043.2−7.8
AA-Briefcase v1.1 EloAgents18011659−7.8
LMArena Agent Arena Confirmed SuccessAgents20.75.4−7.6
Humanity's Last Exam (Text-Only)General QA57.550.1−7.4
CursorBench 4.0Code57.850.4−7.4
BioResearchBenchScience18.011.0−7.0
SnorkelLegalLegal31.438.3+6.9
CUA-benchAgents14.07.2−6.8
SWE-Marathon - release-reported version unspecifiedCode46.353.1+6.8
DAYJOB: HealthcareHealth & Medicine24.718.0−6.7
SciCode 1.0.1 (Artificial Analysis)Code66.960.3−6.6
micro1 PharmaBenchHealth & Medicine10.817.2+6.4
SWE-Marathon v1.1Code46.352.5+6.3
SpatialViz-BenchMultimodal89.783.5−6.2
BullshitBench v2 LeaderboardSafety63.057.0−6.0
GDPval Extended (Mercor held-out rubric score)Professional Work75.870.0−5.8
FrontierCode 1.1 Main (Artificial Analysis)Code52.246.5−5.7
Medical Long Context Reasoning (MLCR-AA, October 2026 methodology)Health & Medicine27.822.2−5.6
SnorkelRevOpsProfessional Work12.518.0+5.5
Epoch Capabilities Index (ECI)Indexes169162−5.4
OncologyBench Strict (25 tasks, October 9 rubric)Health & Medicine29.324.0−5.3
GDPxProfessional Work12.06.8−5.2
Snorkel SWE-bench CLICode16.611.4−5.2
LMArena Agent Arena Bash ReliabilityAgents15.14.8−5.2
CharXiv Extended (Mercor held-out)Multimodal84.779.6−5.1
DataCenterBench Tier 1Agents21.716.7−5.0
Agents' Last Exam v1.1 (ALE v1.1)Agents43.438.5−4.9
JobBench - release-reported mean task rewardProfessional Work75.470.5−4.9
DeepSWE v1.1Code74.278.8+4.6
MASKSafety89.484.9−4.5
APEX-Agents 1.1Professional Work81.377.0−4.3
GDPval-AA v2.1Professional Work18661770−4.2
PCT Political Inconsistency (CAIS)Safety29.133.3−4.2
AA-PersonalityBench Imagination indexChat & Writing94.390.5−3.8
AA-PersonalityBench Informativeness indexChat & Writing90.594.3+3.8
EQ-Bench 4Chat & Writing13401325−3.8
MMLU ProGeneral QA93.489.6−3.8
DTBenchGeneral QA98.995.2−3.7
SnorkelFinance 2.0Finance & Accounting18.615.0−3.6
DAYJOB: AccountingFinance & Accounting34.430.8−3.6
ComplexConstraints (November 2026 rescoring)Chat & Writing64.467.9+3.5
CritPt (avg@5)Science31.728.3−3.4
Excel Modeling Benchmark v1.1Finance & Accounting75.872.5−3.3
Snorkel Agentic Coding 2.0Code40.443.6+3.2
DAYJOB: TaxFinance & Accounting9.26.0−3.2
τ³-Banking (Mercor run, bm25_grep retrieval)Agents55.051.9−3.1
HPCT Refusal (CAIS)Safety100.097.0−3.0
Snorkel WorkplaceAgentsProfessional Work14.417.4+3.0
MacroscopeBenchCode61.464.2+2.8
Snorkel Digital Work IndexIndexes23.626.4+2.8
DAYJOB: FinanceFinance & Accounting23.921.3−2.6
Immigration BenchLegal72.169.6−2.5
BuseyBench SVGMultimodal6.86.6−2.5
Financial Coaching BenchFinance & Accounting76.273.8−2.4
Artificial Analysis Coding Agent Index v1.5Indexes66.063.7−2.3
Creative Writing v3 EloChat & Writing20512007−2.2
AutomationBench-AA - release-reported strict pass rateAgents41.239.1−2.1
MindCube TinyMultimodal93.191.1−2.0
WellnessBenchSafety53.055.0+2.0
IntPhys 2Multimodal68.370.2+1.9
AA-PersonalityBench Expressiveness indexChat & Writing90.588.6−1.9
CharXiv (descriptive and reasoning combined)Multimodal96.494.5−1.9
Ramp Accounting BenchFinance & Accounting50.548.7−1.8
MMMU ProMultimodal86.684.9−1.7
APEX-Accounting 1.1Finance & Accounting65.567.1+1.6
STEMBench120 v1.0.0 (closed-book)Science2.62.7+1.5
HackerRank-BenchCode51.249.7−1.5
MissionReportProfessional Work63.562.1−1.4
GDPval (Mercor 213-task rubric score)Professional Work88.387.0−1.3
Creative Writing v3 Rubric ScoreChat & Writing16.016.2+1.2
CWE-bench v2 Pass@1Cybersecurity67.166.1−1.0
DualEntry Accounting AI BenchmarkFinance & Accounting82.283.2+1.0
Humanity's Sixth SenseMultimodal44.643.7−0.9
SpatialBench V1 Clean RerunsScience72.871.9−0.9
LMArena Text Arena EloChat & Writing15061511+0.9
Access to Justice BenchmarkLegal73.873.0−0.8
Prophet Arena Arena Score (Agentic, OpenCode)Forecasting86.285.4−0.8
LMArena Agent Arena Tool HallucinationAgents0.7-0.5−0.6
OTIS Mock AIME 2024-2025Math100.099.4−0.6
SnorkelUnderwrite 2.0Finance & Accounting22.723.0+0.3
Prophet Arena Arena Score (Fixed Context)Forecasting85.585.2−0.3
AA-LCR Extended (Mercor held-out)Search74.274.4+0.2
GDP.pdfProfessional Work30.630.8+0.2
ERQAMultimodal75.175.3+0.2
BioTIER RefusalSafety98.798.70.0
Dual-Arm Sim (task completion)Agents0.00.00.0
Harvey's Legal Agent Benchmark - Arbitration International Dispute ResolutionLegal0.00.00.0
Harvey's Legal Agent Benchmark - Bankruptcy RestructuringLegal0.00.00.0
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 - Energy Natural ResourcesLegal20.020.00.0
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 - ImmigrationLegal0.00.00.0
Harvey's Legal Agent Benchmark - InsuranceLegal0.00.00.0
Harvey's Legal Agent Benchmark - International Trade SanctionsLegal0.00.00.0
Harvey's Legal Agent Benchmark - Structured Finance SecuritizationLegal0.00.00.0
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 Wondernormalised score marginsData Nov 15, 2026Data: Vals AI, Artificial Analysis, Mercor and 58 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…