Atlas

Compare Models

Inkling 2 Small vs Muse Wonder

Muse Wonder leads by 3.4 capability points (≈95% interval +1.3 to +5.6): a clear lead over Inkling 2 Small · P(higher) ≈ 100%

Wins 74 of 103 shared benchmarks (21 lost, 8 tied)

Capability vs. relative cost
Inkling 2 SmallMuse 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.

Inkling 2 SmallvsMuse Wondercapability vs. relative costData Nov 15, 2026Village LLM Atlasatlas.village.dev

Benchmark wins21 – 74 · 103 shared, 8 tied

Comparing matching setups only (50 benchmarks excluded) · suites counted once
← Inkling 2 SmallMuse Wonder →

Inkling 2 SmallvsMuse Wonderwins by categoryData Nov 15, 2026Data: Vals AI, Artificial Analysis, Surge AI 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 minus Inkling 2 Small.

Terminal-Bench 4.0Code12.649.5+36.9
Code Migration v1.1 (Vals Index v2.2 subset)Code39.569.8+30.3
HLAB-Vals-1.1 - InsuranceLegal0.030.0+30.0
HLAB-Vals-1.1 - Litigation Dispute ResolutionLegal40.010.0−30.0
Terminal-Bench 4.0 (Artificial Analysis)Code13.138.4+25.3
DAYJOB: Finance (October 2026 rescoring)Finance & Accounting14.338.8+24.5
AutomationBench-AA Support and OperationsAgents54.878.7+23.9
AutomationBench-AA Operations, HR, Marketing, Sales and SupportAgents46.069.2+23.2
ComplexConstraints (November 2026 rescoring)Chat & Writing47.667.9+20.3
HLAB-Vals-1.1 - Antitrust CompetitionLegal40.020.0−20.0
HLAB-Vals-1.1 - Arbitration International Dispute ResolutionLegal30.010.0−20.0
HLAB-Vals-1.1 - Banking FinanceLegal10.030.0+20.0
HLAB-Vals-1.1 - Corporate M&ALegal20.040.0+20.0
HLAB-Vals-1.1 - Emerging Companies Venture CapitalLegal20.040.0+20.0
HLAB-Vals-1.1 - Energy Natural ResourcesLegal50.070.0+20.0
HLAB-Vals-1.1 - Environmental ESGLegal0.020.0+20.0
HLAB-Vals-1.1 - Funds Asset ManagementLegal30.010.0−20.0
HLAB-Vals-1.1 - TaxLegal20.00.0−20.0
HLAB-Vals-1.1 - White Collar Defense InvestigationsLegal0.020.0+20.0
Terminal-Bench Science 0.1 (Vals)Science2.922.9+20.0
Terminal-Bench-Science 0.1Science5.725.7+20.0
AutomationBench-AA FinanceAgents43.963.1+19.2
CrossSearch (pass^3)Search23.042.0+19.0
Legal Research Bench ImmigrationLegal27.345.5+18.2
APEX-Agents 1.1Professional Work60.977.0+16.1
CritPt v2 (agentic, avg@5)Science55.771.1+15.4
Legal Research Bench Civil LitigationLegal51.937.0−14.8
DeepFinanceFinance & Accounting29.844.2+14.4
SWE-Marathon v1.1Code38.852.5+13.7
Legal Research Bench FamilyLegal22.736.4+13.6
VIALS-AA (pass^3)Multimodal42.955.3+12.4
HANDBOOK.md Agents v1.1Professional Work17.829.5+11.7
Artificial Analysis Strategy & Ops IndexIndexes43.554.5+11.0
Artificial Analysis Engineering IndexIndexes38.949.6+10.7
Finance Agent v2.1 - General Qualitative AnalysisFinance & Accounting78.067.5−10.5
Humanity's Sixth SenseMultimodal33.343.7+10.4
Humanity's Last Exam DiamondGeneral QA28.739.0+10.3
EnterpriseBench: CoreCraftProfessional Work71.861.5−10.3
Finance Agent v2.1 - ComparablesFinance & Accounting65.055.0−10.0
HLAB-Vals-1.1 - Capital MarketsLegal20.030.0+10.0
HLAB-Vals-1.1 - Data Privacy CybersecurityLegal20.010.0−10.0
HLAB-Vals-1.1 - Healthcare Life SciencesLegal30.020.0−10.0
HLAB-Vals-1.1 - ImmigrationLegal30.040.0+10.0
HLAB-Vals-1.1 - International Trade SanctionsLegal20.030.0+10.0
FrontierMemory v1.1Agents60.051.1−8.9
Finance Agent v2.1 - Market AnalysisFinance & Accounting59.067.7+8.7
Excel Modeling Benchmark v1.1 LBOFinance & Accounting55.964.2+8.4
SciCode 1.0.1 (Artificial Analysis)Code52.360.3+8.0
Artificial Analysis Healthcare & Medical IndexIndexes40.848.7+7.9
CyberBench v1.1 OverallCybersecurity72.780.4+7.6
AA-Briefcase v1.1 EloAgents15271659+7.2
VIALS-AA (average of 3)Multimodal57.864.8+7.0
Legal Research Bench CriminalLegal36.843.9+7.0
Artificial Analysis Finance & Accounting IndexIndexes44.351.1+6.8
Excel Modeling Benchmark v1.1 M&AFinance & Accounting73.780.4+6.7
Legal Research Bench HealthLegal70.076.7+6.7
Vals Science IndexIndexes32.739.1+6.4
GDPval-AA v2.1Professional Work16301770+6.2
Artificial Analysis Economics IndexIndexes43.449.5+6.1
Tax Agent BenchFinance & Accounting65.871.2+5.4
GDP.pdf (Artificial Analysis, All-pass)Professional Work25.230.6+5.4
Artificial Analysis Legal IndexIndexes41.646.9+5.3
Excel Modeling Benchmark v1.1 MiscFinance & Accounting68.363.0−5.3
APEX-Accounting 1.1Finance & Accounting62.067.1+5.1
Excel Modeling Benchmark v1.1 CompsFinance & Accounting73.177.9+4.8
Excel Modeling Benchmark v1.1 TemplateFinance & Accounting71.676.3+4.8
AA-Omniscience v1.1 IndexIndexes16.125.1+4.5
Excel Modeling Benchmark v1.1 DataroomFinance & Accounting83.487.7+4.3
Finance Agent v2.1 - Financial ModelingFinance & Accounting42.438.7−3.7
Finance Agent v2.1 - All PassFinance & Accounting56.653.1−3.5
FrontierCode 2.0 - Pass RateCode25.528.8+3.3
Legal Research Bench Administrative/RegulatoryLegal60.663.6+3.0
Finance Agent v2.1 - General Quantitative AnalysisFinance & Accounting79.282.2+3.0
BioMysteryBench (Vals Terminus 2)Science70.067.0−3.0
SWE Atlas v1.1 - OverallCode61.964.8+2.9
FrontierCode 2.0 - ScoreCode22.625.3+2.7
Finance Agent v2.1 - AdjustmentsFinance & Accounting67.464.7−2.7
Finance Agent v2.1 - Disclosure AnalysisFinance & Accounting80.878.2−2.6
SWE-bench Multimodal (Vals v1, 480 Tasks)Code43.145.6+2.5
Legal Research Bench Business/CommercialLegal46.548.8+2.3
HLAB-Vals-1.1 - Criteria Pass RateLegal93.796.0+2.3
MysteryMechanismScience25.227.5+2.3
sudo L7 (October 2026 rescoring)Code14.116.1+2.0
VIALS-AA (pass@3)Multimodal72.073.9+1.9
Excel Modeling Benchmark v1.1 ScratchFinance & Accounting67.168.8+1.8
Medical Long Context Reasoning (MLCR-AA, October 2026 methodology)Health & Medicine20.622.2+1.7
Vibe Code Bench v1.1Code81.583.1+1.5
Finance Agent v2.1 - PrecedentsFinance & Accounting47.145.6−1.5
Excel Modeling Benchmark v1.1 DCFFinance & Accounting62.263.7+1.4
Finance Agent v2.1 - Earnings AnalysisFinance & Accounting88.990.3+1.4
Arena Code WebDev — ReactCode16591651−1.0
Design Arena Overall Code CategoriesCode13811385+0.7
Excel Modeling Benchmark v1.1 OperatingFinance & Accounting70.070.6+0.7
Arena Code WebDev — HTMLCode16601664+0.6
Legal Research Bench Weighted PassLegal87.987.7−0.1
HLAB-Vals-1.1 - Bankruptcy RestructuringLegal20.020.00.0
HLAB-Vals-1.1 - Corporate GovernanceLegal30.030.00.0
HLAB-Vals-1.1 - Employment LaborLegal0.00.00.0
HLAB-Vals-1.1 - Intellectual PropertyLegal20.020.00.0
HLAB-Vals-1.1 - Real EstateLegal30.030.00.0
HLAB-Vals-1.1 - Structured Finance SecuritizationLegal20.020.00.0
HLAB-Vals-1.1 - Trusts Estates Private ClientLegal20.020.00.0
Legal Research Bench Constitutional/Civil RightsLegal39.539.50.0

Inkling 2 SmallvsMuse Wondernormalised score marginsData Nov 15, 2026Data: Vals AI, Artificial Analysis, Surge AI 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…