Atlas

Compare Models

Gemini 4 Argon vs Muse Wonder Full

Gemini 4 Argon leads by 1.3 capability points (≈95% interval −1.2 to +3.7): statistically tied · P(higher) ≈ 84%

Wins 48 of 102 shared benchmarks (42 lost, 12 tied)

Capability vs. relative cost
Gemini 4 ArgonMuse 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.

Gemini 4 ArgonvsMuse Wonder Fullcapability vs. relative costData Nov 15, 2026Village LLM Atlasatlas.village.dev

Benchmark wins48 – 42 · 102 shared, 12 tied

Comparing matching setups only (2 benchmarks excluded) · suites counted once
← Gemini 4 ArgonMuse Wonder Full →

Gemini 4 ArgonvsMuse Wonder Fullwins by categoryData Nov 15, 2026Data: Vals AI, Artificial Analysis, Arena and 10 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 Gemini 4 Argon.

LisanBench Path LengthGames756032190+76.5
LisanBench Difficulty-WeightedGames38499337+58.8
Harvey's Legal Agent Benchmark - Emerging Companies Venture CapitalLegal40.00.0−40.0
Harvey's Legal Agent Benchmark - Real EstateLegal0.040.0+40.0
SRE Bench — Fully SolvedCode44.311.8−32.4
MASKSafety61.087.3+26.3
IOI (Vals v2)Code100.079.8−20.2
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 MarketsLegal40.020.0−20.0
Harvey's Legal Agent Benchmark - Corporate GovernanceLegal20.040.0+20.0
Harvey's Legal Agent Benchmark - Energy Natural ResourcesLegal20.040.0+20.0
Harvey's Legal Agent Benchmark - Funds Asset ManagementLegal40.020.0−20.0
Harvey's Legal Agent Benchmark - InsuranceLegal0.020.0+20.0
Harvey's Legal Agent Benchmark - International Trade SanctionsLegal20.00.0−20.0
Harvey's Legal Agent Benchmark - Structured Finance SecuritizationLegal0.020.0+20.0
Finance Agent v2 - PrecedentsFinance & Accounting49.835.0−14.8
Finance Agent v2 - Market AnalysisFinance & Accounting79.764.9−14.8
AA-Briefcase v1.1 EloAgents14851729+13.4
Vibe Code Bench 1–100Code21.234.0+12.8
FrontierCode 2.0 (Artificial Analysis)Code25.737.8+12.0
Terminal-Bench-Science 0.1Science48.637.1−11.4
RiemannBench (November 2026 rescoring)Math74.463.2−11.2
MysteryMechanismScience45.535.1−10.4
GDPval-AA v2.1Professional Work16341857+9.9
Robo-benchAgents0.810.4+9.6
SWE-Marathon v1.1Code43.853.1+9.4
Artificial Analysis Coding Agent Index v2.1Indexes45.554.5+9.0
MedCodeHealth & Medicine58.849.9−8.9
SWE-bench Multimodal (Vals v1, 480 Tasks)Code56.047.3−8.7
Medical Long Context Reasoning (MLCR-AA, October 2026 methodology)Health & Medicine13.922.2+8.3
Code Migration v1.1Code70.862.8−8.0
Terminal-Bench Science 0.1 (Vals)Science44.337.1−7.1
Code MigrationCode68.261.0−7.1
AgenticRL-Bench (Verifiable)Agents14.07.0−7.0
GDP.pdf (Artificial Analysis, All-pass)Professional Work25.632.6+7.0
LMArena Agent Arena Bash ReliabilityAgents-5.48.3+6.8
Vals Science IndexIndexes55.448.5−6.8
Finance Agent v2 - All PassFinance & Accounting55.849.0−6.8
Finance Agent v2 - Earnings AnalysisFinance & Accounting84.878.6−6.2
Access to Justice BenchmarkLegal68.574.7+6.2
AutomationBench-AA 1.0.6Agents77.571.3−6.2
Vals RSI Index v1.1 (four tasks)Agents30.624.4−6.1
AA-Omniscience IndexIndexes42.430.1−6.1
Finance Agent v2 - Financial ModelingFinance & Accounting29.823.7−6.1
Humanity's Last Exam DiamondGeneral QA42.548.5+6.0
CritPt (avg@5)Science27.132.9+5.7
Artificial Analysis Coding Agent Index v2.0Indexes53.258.9+5.6
LMArena Code Arena WebDevCode16821723+5.4
ProofBench v1.1Math99.094.0−5.0
LMArena Agent Arena Praise vs ComplaintAgents24.115.4−4.3
CyberBench v1.1 OverallCybersecurity77.973.6−4.2
Finance Agent v2 - ComparablesFinance & Accounting51.046.8−4.1
Tax Agent BenchFinance & Accounting79.075.0−4.0
AA-LCR v1.1Search79.783.7+4.0
Public Benefits Bench v1.1Professional Work69.873.7+4.0
Finance Agent v2 - AdjustmentsFinance & Accounting60.556.7−3.9
HLAB-Vals-1.1Legal27.123.3−3.7
Humanity's Last Exam (Text-Only)General QA57.153.6−3.5
LMArena Agent Arena Net Improvement (Steering Burden)Agents10.79.0−3.4
Excel Modeling BenchmarkFinance & Accounting75.271.9−3.3
Artificial Analysis Intelligence Index v4.3.2Indexes52.655.8+3.2
Immigration BenchLegal68.171.2+3.1
BioMysteryBench (Vals Terminus 2)Science76.373.3−3.0
Finance Agent v2 - Disclosure AnalysisFinance & Accounting74.571.6−2.9
Finance Agent v2 - General Qualitative AnalysisFinance & Accounting77.074.2−2.8
CritPt v2 (agentic, avg@5)Science72.975.1+2.3
ProgramBenchCode2.50.5−2.0
MedScribeHealth & Medicine87.489.3+1.9
Financial Coaching BenchFinance & Accounting73.175.0+1.8
LMArena Agent Arena Steering BurdenAgents13.29.6−1.8
GDPxProfessional Work7.39.0+1.7
Finance Agent v2 - General Quantitative AnalysisFinance & Accounting81.580.1−1.5
Vals Finance IndexIndexes66.064.6−1.4
Legal Research BenchLegal54.853.4−1.4
FrontierCode 1.1 Main (Artificial Analysis)Code43.544.9+1.4
Bug Hunt BenchCode38.740.0+1.3
DeepSWE v1.1Code77.979.0+1.1
Vals Legal IndexIndexes76.877.9+1.1
LMArena Agent Arena Confirmed SuccessAgents13.211.1−1.1
LegalBenchLegal88.387.4−0.9
SciCode 1.0.1 (Artificial Analysis)Code61.862.6+0.8
Harvey HLAB — Criteria Pass RateLegal94.093.5−0.5
Terminal-Bench 4.0Code57.658.1+0.5
Artificial Analysis Progress Index v1Indexes342343+0.5
Artificial Analysis Intelligence Index v5.0.1Indexes50.450.1−0.3
LMArena Agent Arena Tool HallucinationAgents0.50.0−0.2
Excel Modeling Benchmark v1.1Finance & Accounting74.875.0+0.2
Finance Agent v2.1Finance & Accounting67.767.6−0.1
Harvey's Legal Agent Benchmark - Antitrust CompetitionLegal20.020.00.0
Harvey's Legal Agent Benchmark - Corporate M&ALegal20.020.00.0
Harvey's Legal Agent Benchmark - Data Privacy CybersecurityLegal20.020.00.0
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 - ImmigrationLegal20.020.00.0
Harvey's Legal Agent Benchmark - Intellectual PropertyLegal20.020.00.0
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 - Trusts Estates Private ClientLegal40.040.00.0
Harvey's Legal Agent Benchmark - White Collar Defense InvestigationsLegal0.00.00.0

Gemini 4 ArgonvsMuse Wonder Fullnormalised score marginsData Nov 15, 2026Data: Vals AI, Artificial Analysis, Arena and 10 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…