Atlas

Compare Models

Grok 4.7 vs Muse Spark 1.3

Muse Spark 1.3 leads by 0.6 capability points (≈95% interval −1.5 to +2.7): statistically tied · P(higher) ≈ 70%

Wins 113 of 226 shared benchmarks (98 lost, 15 tied)

Capability vs. relative cost
Grok 4.7Muse 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 4.7vsMuse Spark 1.3capability vs. relative costData Nov 15, 2026Village LLM Atlasatlas.village.dev

Benchmark wins98 – 113 · 226 shared, 15 tied

Comparing matching setups only (15 benchmarks excluded) · suites counted once
← Grok 4.7Muse Spark 1.3 →

Grok 4.7vsMuse Spark 1.3wins by categoryData Nov 15, 2026Data: Vals AI, Artificial Analysis, Mercor and 56 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 4.7.

AA-PersonalityBench Informativeness indexChat & Writing33.4100+67.3
AA-PersonalityBench Slop indexChat & Writing8.675.3+67.3
AA-PersonalityBench Imagination indexChat & Writing35.398.1+63.5
Harvey's Legal Agent Benchmark - Corporate GovernanceLegal0.060.0+60.0
Harvey's Legal Agent Benchmark - Data Privacy CybersecurityLegal0.060.0+60.0
AA-PersonalityBench Warmth indexChat & Writing44.896.2+51.9
RSI Arena Stage 1 human ratingAgents1038938−48.1
Design Creativity BenchCode62.247.2−47.8
CheatBenchSafety78.037.0+41.0
Harvey's Legal Agent Benchmark - Bankruptcy RestructuringLegal0.040.0+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
AA-PersonalityBench Organization indexChat & Writing29.663.8+34.6
DistressBenchSafety52.484.9+32.5
FrontierMath Tier 4 (v2) - PrivateMath17.146.3+29.3
ProofBench v1.1Math26.055.0+29.0
SheetBench-50Finance & Accounting14.342.8+28.5
Medical Long Context Reasoning (MLCR-AA)Health & Medicine15.043.3+28.3
SAFE-Teen 106 worst branch: Health Advice (no prompt)Safety39.213.9+25.3
FrontierMath Tiers 1-3 (v2) - PrivateMath53.074.4+21.4
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 - Healthcare Life SciencesLegal20.040.0+20.0
Harvey's Legal Agent Benchmark - Intellectual PropertyLegal20.00.0−20.0
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 - Structured Finance SecuritizationLegal0.020.0+20.0
Harvey's Legal Agent Benchmark - Trusts Estates Private ClientLegal0.020.0+20.0
τ³-Banking (Mercor run, bm25_grep retrieval)Agents32.652.2+19.6
SAFE-Teen 106 worst branch: Urgent Safety (no prompt)Safety44.425.6+18.9
AA-AnalystAgent (pass^5)Professional Work55.037.5−17.5
AA-PersonalityBench Transparency indexChat & Writing58.141.0−17.3
Code MigrationCode44.827.6−17.2
APEX-SWECode53.436.4−17.0
RuneBenchGames5.74.6−16.6
GeneBench-Pro Public Release SubsetScience10.026.0+16.0
SAFE-Teen 106 worst branch: Urgent Safety (under-18 prompt)Safety26.711.3+15.3
Olam Social Poker EloGames15081494−15.2
BrokenArXiv 08/2026 (Native Harnesses)Math35.120.2−14.9
KernelBench CUDA Normalized (RTX PRO 6000)Code45.230.3−14.9
SAFE-Teen 106 worst branch: Health Advice (under-18 prompt)Safety19.24.5+14.7
CyberGym-E2E-AA (Artificial Analysis)Cybersecurity74.059.5−14.5
AutoResearchExam (hidden-test AUARC)Agents0.50.4−14.4
DeepsecBench-AA (Artificial Analysis)Cybersecurity26.912.5−14.4
IOI (Vals v2)Code57.743.9−13.8
Terminal-Bench 4.0Code28.315.2−13.1
WellnessBenchSafety48.061.0+13.0
CWE-bench v1 Programmatic Pass@1Cybersecurity68.055.0−13.0
ChartographyMultimodal14.727.6+12.9
ArXivMath 05/2026Math60.873.3+12.5
Artificial Analysis Cyber Index v1Indexes56.444.3−12.1
SAFE-Teen 106: Health Advice (no prompt)Safety18.76.7+12.0
KernelBench Mega Normalized (RTX PRO 6000)Code18.06.2−11.8
dfbench Detection RecallCybersecurity59.047.4−11.6
GeoBenchMultimodal35254103+11.6
BuseyBench SVGMultimodal4.65.7+11.4
Vision Arena OverallMultimodal12491291+10.9
SnorkelUnderwrite 2.0Finance & Accounting30.519.6−10.9
MysteryMechanismScience25.236.0+10.8
Arena Image-to-WebDevCode15891637+10.6
SnorkelFinance 2.0Finance & Accounting20.210.0−10.2
HANDBOOK.md Agents v1.1Professional Work44.033.9−10.1
Humanity's Last Exam DiamondGeneral QA23.633.7+10.1
SAFE-Teen 106: Health Advice (under-18 prompt)Safety12.02.1+9.9
LMArena Text Arena EloChat & Writing14421496+9.5
Terminal-Bench 4.0 (Artificial Analysis)Code25.816.7−9.1
ITBench-AAAgents42.133.2−8.8
Code2Video-AA EloCode11271019−8.8
AA-Briefcase v1.1 EloAgents16361480−8.5
APEX-1 (Mercor, mean score)Professional Work65.473.9+8.5
SAFE-Teen 106 worst branch: Relationships (no prompt)Safety47.956.2−8.3
Extended NYT Connections 940 (Quadratic v1)Games76.885.1+8.3
Legal Research BenchLegal47.155.3+8.2
MedXpertQA MM Extended (Mercor held-out)Health & Medicine52.060.1+8.1
CritPt (avg@5)Science18.026.0+8.0
Roboflow Vision Evals (September 2026 protocol)Multimodal71.979.8+7.9
Finance Agent v2Finance & Accounting52.360.0+7.7
AutomationBench-AA 1.0.6Agents65.657.9−7.7
Terminal-Bench-Science 0.1Science11.43.8−7.6
CWE-Bench-AA (Artificial Analysis)Cybersecurity68.360.8−7.5
DAXBench v2Code92.685.1−7.4
ChessBench EloGames10761201+7.4
SAFE-Teen 106: Urgent Safety (under-18 prompt)Safety10.12.7+7.4
MentalHealthBenchSafety41.348.6+7.3
MedXpertQA MM (200-question set)Health & Medicine69.076.3+7.3
Snorkel Agentic Coding 2.0Code31.925.0−6.9
APEX-AccountingFinance & Accounting46.753.5+6.8
ArXivMath 06/2026Math70.176.7+6.6
EnterpriseBench: CoreCraftProfessional Work68.261.9−6.3
MineBench — Bradley-Terry RatingGames18481747−6.1
Ruby LLM Benchmarks — Program FixerCode68.074.1+6.1
MatFlowBench Pass@1Science22.816.7−6.1
SAFE-Teen 106: Urgent Safety (no prompt)Safety15.19.0+6.1
CAD ArenaAgents25.831.8+6.0
AA-PersonalityBench Conviction indexChat & Writing82.977.2−5.8
CritPt v2 (agentic, avg@5)Science62.368.0+5.7
AA-3D v1.0 EloCode9921032+5.7
Arena Alignment IndexSafety82.777.1−5.6
ALE-BenchCode18231981+5.6
Humanity's Last Exam (Text-Only)General QA43.148.7+5.6
FrontierCode 2.0 (Artificial Analysis)Code28.723.1−5.5
Creative Writing v3 EloChat & Writing20121907−5.3
FrontierML ($200 wallet)Agents10.916.0+5.1
ChessBench CoherenceGames86.391.2+4.9
Artificial Analysis Coding Agent Index v2.1Indexes41.636.8−4.9
DAYJOB: LawLegal27.622.8−4.8
GDP.pdfProfessional Work22.827.6+4.8
FrontierCode 1.1 Main (Artificial Analysis)Code33.838.6+4.8
CursorBench 4.0Code46.341.6−4.7
Harvey LAB (Mercor run, undisclosed ~213-task cohort)Legal19.515.0−4.5
LMCAGeneral QA49.453.9+4.5
Visa Agentic Commerce BenchmarkAgents60.064.4+4.4
DeepSWE v1.1Code71.075.4+4.4
Tax Agent BenchFinance & Accounting69.073.4+4.4
Vals Index v2Indexes60.264.5+4.3
Harvey HLAB — Criteria Pass RateLegal90.594.7+4.3
Conceptual Reasoning IndexIndexes63.166.2+4.2
RiemannBench (November 2026 rescoring)Math57.653.6−4.0
CadQueryEval (Corrected Geometry)Code88.084.0−4.0
Chess Puzzles (task version 2.0)Games41.037.0−4.0
Mystery Game PuzzlesGames29.025.0−4.0
Snorkel SWE-bench CLICode6.12.2−3.9
LLM Debate BenchmarkChat & Writing16201593−3.9
AA-PersonalityBench Expressiveness indexChat & Writing75.371.4−3.8
GameBench 2Games72.368.5−3.8
GDPval-AA v2.1Professional Work17171631−3.8
FrontierSWE V2Code29.525.8−3.7
SnorkelLegalLegal32.836.5+3.7
LMArena Agent Arena Bash ReliabilityAgents9.32.0−3.7
CharXiv Extended (Mercor held-out)Multimodal78.281.8+3.6
GBENCH One-shot Coding GScoreGames56.352.7−3.6
AA-Omniscience IndexIndexes32.025.0−3.5
BrokenArXiv 05/2026Math40.036.5−3.5
Vibe Code Bench v1.1Code86.282.9−3.3
Vals Index v2.1Indexes54.958.2+3.2
ATLAS (Exa, 200-task subset)Search39.542.7+3.2
Financial Coaching BenchFinance & Accounting74.171.0−3.1
Immigration BenchLegal68.065.0−3.1
Bug Hunt BenchCode27.630.7+3.0
Snorkel Digital Work IndexIndexes19.316.3−3.0
AA-LCR v1.1Search80.083.0+3.0
ComplexConstraintsChat & Writing48.951.9+3.0
DeepFinanceFinance & Accounting34.137.0+2.9
Terminal-Bench Science 0.1 (Vals)Science11.48.6−2.9
SAFE-Teen 106: Relationships (no prompt)Safety31.534.4−2.8
SWE-TogetherCode65.162.4−2.7
LMArena Agent Arena Steering BurdenAgents-2.32.6+2.4
SpeciEval (Pooled English Runs)Safety96.498.7+2.4
SpeciEval (Refusal-Aware Retries, Historical)Safety96.498.8+2.4
ChessBench AccuracyGames74.076.0+2.1
DAYJOB: AccountingFinance & Accounting20.018.0−2.0
TaxCalcBench TY25Finance & Accounting8.06.0−2.0
Westworld Finance Diligence BenchFinance & Accounting47.245.2−2.0
SciCode 1.0.1 (Artificial Analysis)Code57.859.7+2.0
Artificial Analysis Coding Agent Index v1.5Indexes56.354.3−2.0
CharXiv (descriptive and reasoning combined)Multimodal92.093.9+1.9
LMArena Code Arena WebDevCode16411655+1.9
SAFE-Teen 106 worst branch: Relationships (under-18 prompt)Safety5.13.2+1.8
WeirdML v3Science8.56.7−1.8
APEX-Agents 1.1Professional Work68.770.4+1.7
sudo L7Code15.613.9−1.7
Artificial Analysis Intelligence Index v4.3.2Indexes46.448.1+1.6
Ramp Accounting BenchFinance & Accounting44.142.5−1.6
SnorkelManufacturingProfessional Work12.110.5−1.6
Epoch Capabilities Index (ECI)Indexes156158+1.6
Creative Writing v3 Rubric ScoreChat & Writing15.915.6−1.5
HoneyBench v0.2 (hack rate)Safety85.183.6+1.5
Access to Justice BenchmarkLegal73.772.2−1.5
LLM Creative Story WritingChat & Writing0.40.6+1.4
DAYJOB: TaxFinance & Accounting5.03.6−1.4
SnorkelRevOpsProfessional Work11.312.6+1.3
AA-LCR Extended (Mercor held-out)Search68.266.9−1.3
SWE-bench Verified Extended (Mercor held-out)Code55.354.0−1.3
Web Clone BenchCode2.81.5−1.3
ForecastBench Preliminary Dataset Brier IndexForecasting60.761.9+1.2
Artificial Analysis Intelligence Index v5.0.1Indexes35.536.6+1.1
Terminal-Bench 2.1Code73.472.3−1.1
OTIS Mock AIME 2024-2025Math98.199.2+1.1
Artificial Analysis Intelligence Index v5.0Indexes35.336.4+1.1
ACCoRDGeneral QA74.075.1+1.0
Eval Connections One-Shot with TrapsGames85.084.0−1.0
MazeBench ASCIIGames1.00.0−1.0
Realm Financial ReasoningFinance & Accounting44.545.5+1.0
Artificial Analysis Coding Agent Index v2.0Indexes46.645.7−0.9
ArXivMath 08/2026 (Native Harnesses)Math46.545.6−0.9
DAYJOB: Data ScienceProfessional Work6.76.0−0.7
LMArena Agent Arena Net Improvement (Steering Burden)Agents2.62.2−0.7
LMArena Agent Arena Confirmed SuccessAgents5.13.7−0.7
LMArena Agent Arena Praise vs ComplaintAgents3.11.7−0.7
LiveBench 2.0Agents74.174.8+0.7
RSI-Exam 0.1 (Full 88)Agents0.40.4+0.6
LMArena Agent Arena Net ImprovementAgents4.03.8−0.6
SWE-Marathon v1.1Code45.646.3+0.6
Artificial Analysis Progress Index v1Indexes323324+0.6
CVDP (517-problem set)Code54.954.3−0.6
DAYJOB: HealthcareHealth & Medicine8.47.8−0.6
LMArena Agent Arena Bash RecoveryAgents7.26.1−0.6
Vals RSI Index v1.1 (four tasks)Agents20.219.6−0.6
LMArena Agent Arena SteerabilityAgents0.51.6+0.6
Harvey LAB-AA v1.1 (hallucination-gated)Legal9.48.9−0.6
DTBenchGeneral QA96.096.5+0.5
BrokenArXiv 06/2026Math52.853.2+0.5
Excel Modeling BenchmarkFinance & Accounting67.067.4+0.4
SAFE-Teen 106: Relationships (under-18 prompt)Safety1.00.6+0.4
DAYJOB: FinanceFinance & Accounting14.514.8+0.3
GDP.xlsxProfessional Work22.322.6+0.3
SWE-bench Multimodal (Vals v1, 480 Tasks)Code42.943.1+0.2
Longform Creative WritingChat & Writing83.082.8−0.2
LMArena Agent Arena Tool HallucinationAgents1.00.8−0.1
CyberBench v1.1 OverallCybersecurity69.569.4−0.1
AIME 2025Math100.0100.00.0
Harvey's Legal Agent Benchmark - Antitrust CompetitionLegal20.020.00.0
Harvey's Legal Agent Benchmark - Capital MarketsLegal40.040.00.0
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 - Energy Natural ResourcesLegal20.020.00.0
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 - TaxLegal0.00.00.0
Harvey's Legal Agent Benchmark - White Collar Defense InvestigationsLegal0.00.00.0
LegalReasonBenchLegal40.440.40.0
ObviousBenchGeneral QA99.399.30.0
ProgramBenchCode0.50.50.0
SRE Bench — Fully SolvedCode3.83.80.0

Grok 4.7vsMuse Spark 1.3normalised score marginsData Nov 15, 2026Data: Vals AI, Artificial Analysis, Mercor and 56 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…