Atlas

Compare Models

GPT-6 Astra vs Muse Wonder Full

GPT-6 Astra leads by 2.6 capability points (≈95% interval −0.0 to +5.2): statistically tied · P(higher) ≈ 97%

Muse Wonder Full wins 57 of 103 shared benchmarks (38 lost, 8 tied)

Capability vs. relative cost
GPT-6 AstraMuse 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.

GPT-6 AstravsMuse Wonder Fullcapability vs. relative costData Nov 15, 2026Village LLM Atlasatlas.village.dev

Benchmark wins38 – 57 · 103 shared, 8 tied

Comparing matching setups only (33 benchmarks excluded) · suites counted once
← GPT-6 AstraMuse Wonder Full →

GPT-6 AstravsMuse Wonder Fullwins by categoryData Nov 15, 2026Data: Vals AI, Artificial Analysis, Arena and 7 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 GPT-6 Astra.

LisanBench Path LengthGames739332190+77.0
LisanBench Difficulty-WeightedGames31139337+66.7
SRE Bench — Fully SolvedCode56.911.8−45.0
ExploitBench - release-reported exploit progressCybersecurity100.058.9−41.1
Harvey's Legal Agent Benchmark - Corporate GovernanceLegal0.040.0+40.0
Harvey's Legal Agent Benchmark - Energy Natural ResourcesLegal0.040.0+40.0
Harvey's Legal Agent Benchmark - Real EstateLegal0.040.0+40.0
CyberBench v1.1 OverallCybersecurity41.173.6+32.6
Terminal-Bench Science 0.1 (Vals)Science62.937.1−25.7
Terminal-Bench-Science 0.1Science59.537.1−22.4
IOI (Vals v2)Code100.079.8−20.2
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 - Data Privacy CybersecurityLegal0.020.0+20.0
Harvey's Legal Agent Benchmark - Funds Asset ManagementLegal0.020.0+20.0
Harvey's Legal Agent Benchmark - Healthcare Life SciencesLegal0.020.0+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
Harvey's Legal Agent Benchmark - Trusts Estates Private ClientLegal20.040.0+20.0
Medical Long Context Reasoning (MLCR-AA, October 2026 methodology)Health & Medicine41.722.2−19.4
RiemannBench (November 2026 rescoring)Math81.663.2−18.4
MysteryMechanismScience53.235.1−18.0
Code Migration v1.1Code80.662.8−17.8
Vals Science IndexIndexes65.148.5−16.6
HLAB-Vals-1.1Legal7.123.3+16.3
Humanity's Last Exam DiamondGeneral QA63.848.5−15.3
Legal Research BenchLegal39.453.4+13.9
GDPval-AA v2.1Professional Work15871857+11.9
Tax Agent BenchFinance & Accounting63.375.0+11.7
MASKSafety98.587.3−11.2
LMArena Agent Arena Net Improvement (Steering Burden)Agents14.59.0−10.5
Finance Agent v2 - Disclosure AnalysisFinance & Accounting61.771.6+9.9
Vals Legal IndexIndexes68.477.9+9.5
JobBench - release-reported mean task rewardProfessional Work66.175.3+9.2
Finance Agent v2 - Earnings AnalysisFinance & Accounting69.578.6+9.1
Finance Agent v2 - ComparablesFinance & Accounting37.846.8+9.1
Vals Finance IndexIndexes55.664.6+8.9
AA-Briefcase v1.1 EloAgents15691729+8.8
Finance Agent v2 - All PassFinance & Accounting40.349.0+8.8
Finance Agent v2 - AdjustmentsFinance & Accounting48.356.7+8.4
LMArena Agent Arena Praise vs ComplaintAgents31.715.4−8.1
CritPt v2 (agentic, avg@5)Science83.175.1−8.0
Financial Coaching BenchFinance & Accounting67.575.0+7.4
Finance Agent v2.1Finance & Accounting60.467.6+7.1
AA-Omniscience IndexIndexes43.730.1−6.8
Artificial Analysis Intelligence Index v5.0.1Indexes56.950.1−6.8
Code MigrationCode67.761.0−6.7
Artificial Analysis Engineering IndexIndexes61.855.3−6.5
Vibe Code Bench 1–100Code27.634.0+6.3
SciCode 1.0.1 (Artificial Analysis)Code56.562.6+6.1
Harvey HLAB — Criteria Pass RateLegal87.593.5+6.0
BioMysteryBench (Vals Terminus 2)Science79.373.3−5.9
Finance Agent v2 - General Qualitative AnalysisFinance & Accounting68.474.2+5.8
Artificial Analysis Intelligence Index v5.0Indexes55.349.7−5.5
OSWorld 2.1 full - reported binary completion, step limit unspecifiedAgents34.339.4+5.1
ProgramBenchCode5.50.5−5.0
ProofBench v1.1Math99.094.0−5.0
DeepSWE v1.1Code74.179.0+4.9
Artificial Analysis Legal IndexIndexes55.650.7−4.8
Finance Agent v2 - PrecedentsFinance & Accounting30.335.0+4.7
FrontierCode 2.0 (Artificial Analysis)Code42.437.8−4.6
SWE-bench Multimodal (Vals v1, 480 Tasks)Code43.347.3+4.0
AutomationBench-AA - release-reported strict pass rateAgents41.645.4+3.8
AA-LCR v1.1Search80.083.7+3.7
Immigration BenchLegal67.771.2+3.5
Artificial Analysis Intelligence Index v4.3.2Indexes52.755.8+3.1
Artificial Analysis Economics IndexIndexes57.254.1−3.1
AutomationBench-AA 1.0.6Agents68.571.3+2.8
LMArena Agent Arena Steering BurdenAgents14.89.6−2.6
OSWorld 2.1 full - reported partial reward, step limit unspecifiedAgents75.878.4+2.6
Excel Modeling Benchmark v1.1Finance & Accounting72.775.0+2.3
Artificial Analysis Progress Index v1Indexes350343−2.2
Finance Agent v2 - Financial ModelingFinance & Accounting21.623.7+2.2
Artificial Analysis Finance & Accounting IndexIndexes57.455.2−2.1
FrontierCode 1.1 Main (Artificial Analysis)Code47.044.9−2.1
Artificial Analysis Healthcare & Medical IndexIndexes53.751.9−1.8
Terminal-Bench 4.0Code59.658.1−1.5
LMArena Agent Arena Confirmed SuccessAgents14.011.1−1.5
MedCodeHealth & Medicine48.549.9+1.4
MedScribeHealth & Medicine87.989.3+1.4
Finance Agent v2 - General Quantitative AnalysisFinance & Accounting78.880.1+1.3
CritPt (avg@5)Science31.732.9+1.1
GDP.pdfProfessional Work34.233.2−1.0
Finance Agent v2 - Market AnalysisFinance & Accounting65.564.9−0.6
GDPxProfessional Work9.69.0−0.6
Humanity's Last Exam (Text-Only)General QA53.153.6+0.6
LMArena Agent Arena Tool HallucinationAgents1.00.0−0.5
LMArena Agent Arena Bash ReliabilityAgents7.88.3+0.2
Excel Modeling BenchmarkFinance & Accounting71.771.9+0.2
Artificial Analysis Strategy & Ops IndexIndexes58.057.9−0.1
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 - Environmental ESGLegal0.00.00.0
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

GPT-6 AstravsMuse Wonder Fullnormalised score marginsData Nov 15, 2026Data: Vals AI, Artificial Analysis, Arena and 7 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…