Atlas

Compare Models

Claude Opus 5 vs Muse Wonder

Claude Opus 5 leads by 0.5 capability points (≈95% interval −1.8 to +2.9): statistically tied · P(higher) ≈ 67%

Wins 77 of 162 shared benchmarks (71 lost, 14 tied)

Capability vs. relative cost
Claude Opus 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 5vsMuse Wondercapability vs. relative costData Nov 15, 2026Village LLM Atlasatlas.village.dev

Benchmark wins77 – 71 · 162 shared, 14 tied

Comparing matching setups only (10 benchmarks excluded) · suites counted once
← Claude Opus 5Muse Wonder →

Claude Opus 5vsMuse Wonderwins by categoryData Nov 15, 2026Data: Vals AI, Artificial Analysis, Center for AI Safety and 40 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.

DeepResearch Bench II (Mercor 130-task set)Search56.110.8−45.3
Harvey's Legal Agent Benchmark - Litigation Dispute ResolutionLegal0.040.0+40.0
Machiavelli Deception (CAIS)Safety96.583.6+39.0
LisanBench Path LengthGames1542827973+39.0
ChessBench CoherenceGames63.8100.0+36.2
LisanBench Difficulty-WeightedGames50688303+34.6
CheatBenchSafety45.312.7+32.7
BioSecBench-Refusal V1 Clean RerunsSafety24.555.3+30.8
VCT-Refusal (CAIS)Safety29.460.2+30.8
VoxelBench Text RatingGames23001870−30.6
HiL-Bench (Human-in-Loop Benchmark)Agents57.079.7+22.7
LLM Creative Story WritingChat & Writing3.72.0−20.0
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 - 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 - Structured Finance SecuritizationLegal20.00.0−20.0
Harvey's Legal Agent Benchmark - Trusts Estates Private ClientLegal0.020.0+20.0
SnorkelManufacturingProfessional Work9.427.8+18.4
IOI (Vals v2)Code84.366.9−17.4
BullshitBench v2 LeaderboardSafety73.057.0−16.0
OncologyBench Strict (25 tasks, October 9 rubric)Health & Medicine40.024.0−16.0
DistressBenchSafety70.285.9+15.7
ProofBench v1.1Math99.084.0−15.0
EBR-bench v4 (card ban, single agent)Games45.731.4−14.3
Humanity's Sixth SenseMultimodal30.543.7+13.2
ChessBench EloGames8261046+13.1
BioMysteryBench (Vals Terminus 2)Science79.367.0−12.2
SnorkelLegalLegal26.438.3+11.9
AutomationBench-AA 1.0.6Agents56.668.1+11.5
RuneBenchGames5.75.0−11.5
Vending-Bench 2Games111829432−10.6
EQ-Bench 4Chat & Writing13651325−10.5
LMArena Agent Arena Net Improvement (Steering Burden)Agents7.21.8−10.3
GBENCH One-shot Coding GScoreGames68.158.1−10.1
DAYJOB: FinanceFinance & Accounting11.321.3+10.0
MysteryMechanismScience37.427.5−9.9
DAYJOB: HealthcareHealth & Medicine8.418.0+9.6
SpeciEval (Pooled English Runs)Safety87.997.5+9.6
NoCoT-Bench NCRI 15.2General QA11597.7−9.5
Conceptual Reasoning IndexIndexes74.767.7−9.5
APEX-SWECode63.754.6−9.1
GDP.pdf (Artificial Analysis, All-pass)Professional Work21.630.6+9.0
MMMU-Pro Extended (Mercor held-out)Multimodal34.343.2+8.9
Vals Science IndexIndexes47.939.1−8.8
Humanity's Last ExamGeneral QA56.447.6−8.8
MASKSafety93.484.9−8.5
MineBench — Bradley-Terry RatingGames20081868−8.5
Medical Long Context Reasoning (MLCR-AA, October 2026 methodology)Health & Medicine13.922.2+8.3
CrossSearch (pass^3)Search34.042.0+8.0
Mystery Game PuzzlesGames59.051.0−8.0
τ³-Banking (Mercor run, bm25_grep retrieval)Agents44.051.9+7.9
EnigmaEvalGeneral QA43.936.1−7.8
SpatialViz-BenchMultimodal75.883.5+7.7
ACCoRDGeneral QA83.876.2−7.7
LMCAGeneral QA64.556.8−7.6
Terminal-Bench 4.0 (Artificial Analysis)Code46.038.4−7.6
HardGeoBench <=100miMultimodal46.338.8−7.5
micro1 PharmaBenchHealth & Medicine9.717.2+7.5
EnterpriseBench: CoreCraftProfessional Work68.761.5−7.2
HackerRank-BenchCode42.649.7+7.1
GDPval Extended (Mercor held-out rubric score)Professional Work62.970.0+7.1
VIALSMultimodal24.431.5+7.1
GameBench 2Games84.877.8−7.0
LMArena Agent Arena Praise vs ComplaintAgents12.2-1.8−7.0
NoCoT-Bench NCKI (kspine v3)General QA119109−6.9
MindCube TinyMultimodal84.391.1+6.7
Public Benefits Bench v1.1Professional Work76.970.2−6.7
Furniture Assembly BenchmarkMultimodal60.854.2−6.7
APEX-1 (Mercor, mean score)Professional Work68.675.1+6.5
Creative Writing v3 EloChat & Writing21352007−6.5
Excel Modeling BenchmarkFinance & Accounting73.667.1−6.5
TextQuests Average Cumulative HarmSafety22.620.8+6.4
SnorkelRevOpsProfessional Work12.218.0+5.8
Humanity's Last Exam DiamondGeneral QA44.839.0−5.8
AA-Omniscience IndexIndexes37.125.5−5.8
TextQuests Game ProgressGames53.347.6−5.7
DeepSWE v1.1Code73.278.8+5.6
LMArena Code Arena WebDevCode16911649−5.5
Tax Agent BenchFinance & Accounting76.771.2−5.5
Vibe Code Bench v1.1Code88.483.1−5.3
Code MigrationCode57.562.6+5.1
IntPhys 2Multimodal65.170.2+5.1
Harvey HLAB — Criteria Pass RateLegal87.792.7+5.0
HardGeoBench <=10miMultimodal32.527.5−5.0
Legal Research BenchLegal55.350.5−4.8
MacroscopeBenchCode59.464.2+4.8
Snorkel Agentic Coding 2.0Code38.943.6+4.7
SnorkelUnderwrite 2.0Finance & Accounting18.323.0+4.7
Snorkel Digital Work IndexIndexes21.826.4+4.7
HardGeoBench Avg DistanceMultimodal12181369−4.6
Bug Hunt BenchCode25.730.2+4.4
ERQAMultimodal70.875.3+4.4
Terminal-Bench Science 0.1 (Vals)Science27.122.9−4.3
LiveBench 2.0Agents82.178.1−4.0
Artificial Analysis Coding Agent Index v1.5Indexes59.763.7+3.9
SciCode 1.0.1 (Artificial Analysis)Code56.460.3+3.9
CursorBench 4.0Code46.650.4+3.8
SWE-Marathon v1.1Code48.852.5+3.8
LMArena Text Arena EloChat & Writing14901511+3.7
Toloka Arena (v3)Agents62.065.7+3.7
FrontierMath Tiers 1-3 (v2) - PrivateMath85.682.1−3.5
SpatialBench V1 Clean RerunsScience68.471.9+3.5
PCT Political Inconsistency (CAIS)Safety36.733.3+3.4
HPCT Refusal (CAIS)Safety100.097.0−3.0
BuseyBench SVGMultimodal6.36.6+3.0
Terminal-Bench-Science 0.1Science28.625.7−2.9
FrontierCode 2.0 - ScoreCode28.125.3−2.8
APEX-Accounting 1.1Finance & Accounting64.367.1+2.8
DTBenchGeneral QA97.995.2−2.7
Snorkel SWE-bench CLICode14.011.4−2.6
FrontierCode 2.0 - Pass RateCode31.428.8−2.6
Snorkel WorkplaceAgentsProfessional Work14.917.4+2.5
LMArena Agent Arena Bash ReliabilityAgents9.84.8−2.5
FrontierMath Tier 4 (v2) - PrivateMath73.270.7−2.4
MMLU ProGeneral QA92.089.6−2.4
LMArena Agent Arena Confirmed SuccessAgents10.25.4−2.4
DAXBench v2Code86.284.0−2.1
TaxCalcBench TY25Finance & Accounting20.022.0+2.0
VulnPR-100Code48.046.0−2.0
Epoch Capabilities Index (ECI)Indexes164162−2.0
CUA-benchAgents9.07.2−1.8
GDPval-AA v2.1Professional Work17291770+1.8
Artificial Analysis Intelligence Index v4.3.2Indexes50.852.4+1.6
SciCode (main problems)Science17.315.8−1.5
SnorkelFinance 2.0Finance & Accounting16.515.0−1.5
GDPval (Mercor 213-task rubric score)Professional Work85.687.0+1.4
BioTIER RefusalSafety100.098.7−1.3
HardGeoBench Country AccuracyMultimodal53.852.5−1.2
Eval Connections One-Shot with TrapsGames74.073.0−1.0
LMArena Agent Arena Steering BurdenAgents4.42.6−0.9
MMMU ProMultimodal84.084.9+0.9
ChessBench AccuracyGames71.070.2−0.9
CritPt (avg@5)Science29.128.3−0.9
LMArena Agent Arena Tool HallucinationAgents0.9-0.5−0.7
Artificial Analysis Progress Index v1Indexes334336+0.7
Artificial Analysis Intelligence Index v5.0.1Indexes44.243.6−0.6
OTIS Mock AIME 2024-2025Math98.999.4+0.6
AA-LCR Extended (Mercor held-out)Search73.974.4+0.5
CritPt v2 (agentic, avg@5)Science71.471.1−0.3
AA-Briefcase v1.1 EloAgents16541659+0.2
Creative Writing v3 Rubric ScoreChat & Writing16.316.2−0.2
CharXiv Extended (Mercor held-out)Multimodal79.879.6−0.2
CharXiv (descriptive and reasoning combined)Multimodal94.694.5−0.1
APEX-Agents 1.1Professional Work77.077.00.0
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 - Corporate M&ALegal20.020.00.0
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 - TaxLegal0.00.00.0
Harvey's Legal Agent Benchmark - White Collar Defense InvestigationsLegal0.00.00.0

Claude Opus 5vsMuse Wondernormalised score marginsData Nov 15, 2026Data: Vals AI, Artificial Analysis, Center for AI Safety and 40 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…