Atlas

Compare Models

Grok 4.6 vs Muse Spark 1.3

Muse Spark 1.3 leads by 1.2 capability points (≈95% interval −0.8 to +3.2): statistically tied · P(higher) ≈ 88%

Wins 113 of 184 shared benchmarks (58 lost, 13 tied)

Capability vs. relative cost
Grok 4.6Muse Spark 1.3Closed 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.

Grok 4.6vsMuse Spark 1.3capability vs. relative costData Nov 15, 2026Village LLM Atlasatlas.village.dev

Benchmark wins58 – 113 · 184 shared, 13 tied

Comparing matching setups only (11 benchmarks excluded) · suites counted once
← Grok 4.6Muse Spark 1.3 →

Grok 4.6vsMuse Spark 1.3wins by categoryData Nov 15, 2026Data: Vals AI, Artificial Analysis, Mercor and 47 othersVillage LLM Atlasatlas.village.dev

Margins

Each benchmark scaled 0–100% (its declared range, else the field’s range); Δ is Muse Spark 1.3 minus Grok 4.6.

AA-PersonalityBench Imagination indexChat & Writing20.098.1+78.8
AA-PersonalityBench Warmth indexChat & Writing31.596.2+65.4
AA-PersonalityBench Informativeness indexChat & Writing44.8100+55.8
AA-PersonalityBench Organization indexChat & Writing14.363.8+50.0
BabaIsBench Stage 0: The IntroGames96.046.0−50.0
AA-PersonalityBench Slop indexChat & Writing35.375.3+40.4
Harvey's Legal Agent Benchmark - Bankruptcy RestructuringLegal0.040.0+40.0
Harvey's Legal Agent Benchmark - Capital MarketsLegal0.040.0+40.0
Harvey's Legal Agent Benchmark - Corporate GovernanceLegal20.060.0+40.0
Harvey's Legal Agent Benchmark - Data Privacy CybersecurityLegal20.060.0+40.0
Harvey's Legal Agent Benchmark - Emerging Companies Venture CapitalLegal0.040.0+40.0
Harvey's Legal Agent Benchmark - ImmigrationLegal0.040.0+40.0
LLM Creative Story WritingChat & Writing-2.90.6+38.9
Gray Swan IPI Attack Success (k=15)Safety51.815.9+35.9
Document ArenaProfessional Work14381473+31.2
Medical Long Context Reasoning (MLCR-AA)Health & Medicine12.243.3+31.1
VoxelBench Text RatingGames20501616−30.9
AA-PersonalityBench Transparency indexChat & Writing71.441.0−30.8
RuneBenchGames6.34.6−26.1
InferenceBenchCode6.74.5−25.3
SWE-bench Verified Extended (Mercor held-out)Code78.054.0−24.0
ClockBench AccuracyMultimodal20.042.2+22.2
ChessBench CoherenceGames69.291.2+22.0
APEX-SWECode57.736.4−21.3
Harvey's Legal Agent Benchmark - Arbitration International Dispute ResolutionLegal0.020.0+20.0
Harvey's Legal Agent Benchmark - Energy Natural ResourcesLegal40.020.0−20.0
Harvey's Legal Agent Benchmark - Healthcare Life SciencesLegal20.040.0+20.0
Harvey's Legal Agent Benchmark - International Trade SanctionsLegal0.020.0+20.0
Harvey's Legal Agent Benchmark - Litigation Dispute ResolutionLegal20.00.0−20.0
Harvey's Legal Agent Benchmark - Real EstateLegal0.020.0+20.0
Harvey's Legal Agent Benchmark - Trusts Estates Private ClientLegal0.020.0+20.0
ChessBench EloGames8911201+18.4
WellnessBenchSafety43.061.0+18.0
Hedge-BenchFinance & Accounting26.49.1−17.4
WordleBenchGames89.073.0−16.0
ComplexConstraintsChat & Writing36.551.9+15.4
AA-PersonalityBench Conviction indexChat & Writing92.477.2−15.4
HackerRank-BenchCode27.742.9+15.2
SnorkelFinance 2.0Finance & Accounting25.110.0−15.1
FrontierMath Tier 4 (v2) - PrivateMath31.746.3+14.6
SWE-Marathon v1.1Code31.946.3+14.4
Humanity's Last Exam DiamondGeneral QA21.533.7+12.2
Design Creativity BenchCode43.447.2+12.1
CadQueryEval (Corrected Geometry)Code72.084.0+12.0
HANDBOOK.mdProfessional Work27.315.4−11.9
MedXpertQA MM Extended (Mercor held-out)Health & Medicine48.460.1+11.7
AutoResearchExam (hidden-test AUARC)Agents0.50.4−11.4
Roboflow Vision Evals (September 2026 protocol)Multimodal68.779.8+11.1
GeneBench-Pro Public Release SubsetScience15.026.0+11.0
BuseyBench SVGMultimodal4.65.7+11.0
GDP.pdfProfessional Work17.227.6+10.4
Vibe Code Bench v1.1Code76.285.9+9.6
AutomationBench-AA 1.0.6Agents67.057.9−9.1
Mystery Game PuzzlesGames34.025.0−9.0
IOI (Vals v2)Code47.656.6+8.9
LMArena Agent Arena Net ImprovementAgents1.13.8+8.9
ChessBench AccuracyGames67.876.0+8.8
Snorkel Agentic Coding 2.0Code33.625.0−8.6
FrontierMath Tiers 1-3 (v2) - PrivateMath66.074.4+8.4
DeepSWE v1.1Code67.575.4+7.9
SpeciEval (Refusal-Aware Retries, Historical)Safety90.898.8+7.9
SpeciEval (Pooled English Runs)Safety90.898.7+7.9
MMMU-Pro Extended (Mercor held-out)Multimodal26.033.8+7.8
AA-PersonalityBench Expressiveness indexChat & Writing63.871.4+7.7
KernelBench CUDA Normalized (RTX PRO 6000)Code37.730.3−7.4
Artificial Analysis Coding Agent Index v1.5Indexes47.054.3+7.3
Vision Arena OverallMultimodal12631291+7.3
Legal Research BenchLegal48.155.3+7.2
ChartographyMultimodal20.527.6+7.1
Eval Connections One-Shot with TrapsGames91.084.0−7.0
ProofBench v1.1Math51.058.0+7.0
LMArena Text Arena EloChat & Writing14561496+7.0
CheatBenchSafety79.686.5−6.9
APEX-Agents 1.1Professional Work77.370.4−6.9
Arena Image-to-WebDevCode16071637+6.6
NoCoT-Bench NCRI 15.2General QA86.898.3+6.3
CritPt (avg@5)Science19.726.0+6.3
Finance Agent v2Finance & Accounting53.760.0+6.3
APEX-1 (Mercor, mean score)Professional Work67.773.9+6.2
KernelBench Mega Normalized (RTX PRO 6000)Code0.06.2+6.2
Vals Index v2.1Indexes52.158.2+6.1
GDPval Extended (Mercor held-out rubric score)Professional Work61.855.9−5.9
SnorkelManufacturingProfessional Work16.410.5−5.9
SimpleBenchGeneral QA75.981.8+5.9
Vals RSI Index v1.1 (four tasks)Agents25.519.6−5.8
Humanity's Last Exam (Text-Only)General QA42.948.7+5.8
CritPt v2 (agentic, avg@5)Science62.368.0+5.7
ALE-BenchCode18221981+5.6
Artificial Analysis Intelligence Index v5.0.1Indexes31.036.6+5.6
Olam Social Poker EloGames14991494−5.4
LMCAGeneral QA48.553.9+5.4
MysteryMechanismScience30.636.0+5.4
Vals Index v2Indexes59.264.5+5.4
Extended NYT Connections 940 (Quadratic v1)Games80.085.1+5.1
Conceptual Reasoning IndexIndexes62.566.2+5.1
CyberBench v1.1 OverallCybersecurity67.772.7+5.1
DAYJOB: HealthcareHealth & Medicine2.87.8+5.0
Shroombench (mushroom identification, top-1)Multimodal44.049.0+5.0
LMArena Code Arena WebDevCode16181655+4.9
Excel Modeling BenchmarkFinance & Accounting62.767.4+4.7
APEX-Accounting 1.1Finance & Accounting60.364.9+4.6
CharXiv Extended (Mercor held-out)Multimodal77.381.8+4.5
LMArena Agent Arena Net Improvement (Steering Burden)Agents-0.22.2+4.5
Snorkel Digital Work IndexIndexes20.516.3−4.2
SnorkelLegalLegal40.736.5−4.2
LMArena Agent Arena Bash ReliabilityAgents10.02.0−4.0
Chess Puzzles (task version 2.0)Games33.037.0+4.0
MineBench — Bradley-Terry RatingGames18111747−3.9
Artificial Analysis Intelligence Index v4.3.2Indexes44.348.1+3.8
Artificial Analysis Intelligence Index v4.3Indexes44.448.2+3.8
AA-AnalystAgent (pass^5)Professional Work41.337.5−3.7
Real-SWECode32.536.3+3.8
CVDP (517-problem set)Code58.054.3−3.7
EnterpriseBench: CoreCraftProfessional Work65.661.9−3.7
Arena Alignment IndexSafety80.877.1−3.7
AA-Briefcase EloAgents15451483−3.6
Snorkel SWE-bench CLICode5.72.2−3.5
ACCoRDGeneral QA71.675.1+3.5
Bug Hunt BenchCode27.330.7+3.4
FrontierCode 2.0 (Artificial Analysis)Code19.823.1+3.4
SciCode 1.0.1 (Artificial Analysis)Code56.559.7+3.2
SnorkelRevOpsProfessional Work15.812.6−3.2
LMArena Agent Arena Confirmed SuccessAgents-2.63.7+3.2
CAD ArenaAgents34.831.8−2.9
Vals RSI Index v1.1 (historical five tasks)Agents21.518.7−2.9
Code MigrationCode44.647.4+2.8
AA-Omniscience IndexIndexes30.525.0−2.7
GBENCH One-shot Coding GScoreGames55.452.7−2.6
Terminal-Bench 2.1Code88.085.4−2.6
Terminal-Bench 4.0Code25.327.8+2.5
RSI-Exam 0.1 (Full 88)Agents0.40.4+2.4
Harvey HLAB — Criteria Pass RateLegal92.594.7+2.2
LMArena Agent Arena Steering BurdenAgents-1.82.6+2.2
LMArena Agent Arena Praise vs ComplaintAgents-2.51.7+2.1
Tax Agent BenchFinance & Accounting71.473.4+2.0
DAYJOB: FinanceFinance & Accounting12.814.8+2.0
AA-LCR v1.1Search81.083.0+2.0
CWE-bench v1 Programmatic Pass@1Cybersecurity57.055.0−2.0
SnorkelUnderwrite 2.0Finance & Accounting17.819.6+1.8
SWE-TogetherCode60.662.4+1.8
AA-LCR Extended (Mercor held-out)Search65.266.9+1.7
LLM Debate BenchmarkChat & Writing16041593−1.6
ProgramBenchCode1.02.5+1.5
Terminal-Bench Science 0.1 (Vals)Science11.410.0−1.4
micro1 PharmaBenchHealth & Medicine12.513.9+1.4
GDPval-AA v2.1Professional Work16581631−1.2
MedXpertQA MM (200-question set)Health & Medicine75.276.3+1.1
DAXBench v2Code86.285.1−1.1
Artificial Analysis Progress Index v1Indexes322324+1.0
CharXiv (descriptive and reasoning combined)Multimodal92.993.9+1.0
Immigration BenchLegal66.065.0−1.0
Terminal-Bench-Science 0.1Science2.93.8+1.0
ForecastBench Preliminary Dataset Brier IndexForecasting61.061.9+0.9
Realm Financial ReasoningFinance & Accounting44.645.5+0.9
LMArena Agent Arena SteerabilityAgents3.31.6−0.8
Access to Justice BenchmarkLegal71.372.2+0.8
GPQA Diamond (Artificial Analysis avg@5)General QA94.994.1−0.8
DTBenchGeneral QA97.396.5−0.8
NoCoT-Bench NCKI (kspine v3)General QA112113+0.7
ObviousBenchGeneral QA100.099.3−0.7
FrontierSWE V2Code25.325.8+0.5
Terminal-Bench 4.0 (Artificial Analysis)Code17.216.7−0.5
𝜏³-BankingAgents50.750.5−0.2
GameBench 2Games68.768.5−0.2
CursorBench 4.0Code41.441.6+0.2
LMArena Agent Arena Bash RecoveryAgents5.76.1+0.2
LiveBench 2.0Agents74.974.8−0.2
LMArena Agent Arena Tool HallucinationAgents1.00.8−0.1
ForecastBench Tournament Overall Brier IndexForecasting65.865.9+0.1
Epoch Capabilities Index (ECI)Indexes1581580.0
GDPval-AA v2Professional Work166316620.0
AIME 2025Math100.0100.00.0
Harvey's Legal Agent Benchmark - Antitrust CompetitionLegal20.020.00.0
Harvey's Legal Agent Benchmark - Banking FinanceLegal20.020.00.0
Harvey's Legal Agent Benchmark - Corporate M&ALegal20.020.00.0
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 - Funds Asset ManagementLegal20.020.00.0
Harvey's Legal Agent Benchmark - InsuranceLegal0.00.00.0
Harvey's Legal Agent Benchmark - Intellectual PropertyLegal0.00.00.0
Harvey's Legal Agent Benchmark - Structured Finance SecuritizationLegal20.020.00.0
Harvey's Legal Agent Benchmark - TaxLegal0.00.00.0
Harvey's Legal Agent Benchmark - White Collar Defense InvestigationsLegal0.00.00.0
OTIS Mock AIME 2024-2025Math99.299.20.0

Grok 4.6vsMuse Spark 1.3normalised score marginsData Nov 15, 2026Data: Vals AI, Artificial Analysis, Mercor and 47 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…