Atlas

Compare Models

Claude Opus 5 vs Muse Spark 1.3

Claude Opus 5 leads by 2.9 capability points (≈95% interval +0.7 to +5.1): a clear lead over Muse Spark 1.3 · P(higher) ≈ 99%

Wins 120 of 187 shared benchmarks (55 lost, 12 tied)

Capability vs. relative cost
Claude Opus 5Muse 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.

Claude Opus 5vsMuse Spark 1.3capability vs. relative costData Nov 15, 2026Village LLM Atlasatlas.village.dev

Benchmark wins120 – 55 · 187 shared, 12 tied

Comparing matching setups only (42 benchmarks excluded) · suites counted once
← Claude Opus 5Muse Spark 1.3 →

Claude Opus 5vsMuse Spark 1.3wins by categoryData Nov 15, 2026Data: Vals AI, Artificial Analysis, Arena and 54 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 Claude Opus 5.

KernelBench Mega Normalized (H100)Code100.012.4−87.6
Harvey's Legal Agent Benchmark - Corporate GovernanceLegal0.060.0+60.0
Harvey's Legal Agent Benchmark - Data Privacy CybersecurityLegal0.060.0+60.0
BabaIsBench Stage 0: The IntroGames100.046.0−54.0
InferenceBenchCode8.94.5−52.1
VoxelBench Text RatingGames23001616−48.7
ProofBench v1.1Math99.058.0−41.0
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 - Emerging Companies Venture CapitalLegal0.040.0+40.0
Harvey's Legal Agent Benchmark - ImmigrationLegal0.040.0+40.0
RiemannBenchMath68.028.0−40.0
BrokenArXiv 06/2026Math90.753.2−37.5
LLM Creative Story WritingChat & Writing3.70.6−35.9
Mystery Game PuzzlesGames59.025.0−34.0
Document ArenaProfessional Work15091473−32.0
SWE-bench Verified Extended (Mercor held-out)Code82.054.0−28.0
IOI (Vals v2)Code84.356.6−27.8
ChessBench CoherenceGames63.891.2+27.4
FrontierMath Tier 4 (v2) - PrivateMath73.246.3−26.8
FrontierSWE V2Code52.025.8−26.2
Terminal-Bench 4.0Code53.927.8−26.2
Olam Social Poker EloGames15181494−26.1
BizAgentBench (strict success)Agents64.038.0−26.0
APEX-SWECode63.739.1−24.6
WordleBenchGames96.073.0−23.0
ALE-BenchCode26221981−22.7
ChessBench EloGames8261201+22.3
TextQuests Game ProgressGames53.333.0−20.4
AutoResearchExam (hidden-test AUARC)Agents0.60.4−20.0
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 - Funds Asset ManagementLegal0.020.0+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 - Real EstateLegal0.020.0+20.0
Harvey's Legal Agent Benchmark - Trusts Estates Private ClientLegal0.020.0+20.0
Hedge-BenchFinance & Accounting29.09.1−19.9
LMArena Agent Arena Net ImprovementAgents9.53.8−18.8
LLM Debate BenchmarkChat & Writing17241593−18.7
Terminal-Bench-Science 0.1Science28.611.0−17.6
RuneBenchGames5.74.6−17.6
Terminal-Bench Science 0.1 (Vals)Science27.110.0−17.1
HANDBOOK.mdProfessional Work32.315.4−16.9
GameBench 2Games84.868.5−16.3
AA-AnalystAgent (pass^5)Professional Work53.837.5−16.2
Medical Long Context Reasoning (MLCR-AA)Health & Medicine59.443.3−16.1
MineBench — Bradley-Terry RatingGames20081747−15.8
APEX-Agents 1.1Professional Work77.061.3−15.7
Terminal-Bench 4.0 (Artificial Analysis)Code49.033.3−15.7
GBENCH One-shot Coding GScoreGames68.152.7−15.4
KernelBench CUDA Normalized (RTX PRO 6000)Code45.530.3−15.2
DistressBenchSafety70.284.9+14.7
ComplexConstraintsChat & Writing37.351.9+14.6
TaxCalcBench TY25Finance & Accounting20.06.0−14.0
Snorkel Agentic Coding 2.0Code38.925.0−13.9
Vals RSI Index v1.1 (historical five tasks)Agents32.118.7−13.4
Vals RSI Index v1.1 (four tasks)Agents33.019.6−13.4
DeepsecBench-AA (Artificial Analysis)Cybersecurity25.912.5−13.3
WorldAuditBenchMultimodal28.215.0−13.2
Humanity's Last ExamGeneral QA56.443.2−13.2
Snorkel SWE-bench CLICode14.02.2−11.8
Conceptual Reasoning IndexIndexes74.766.2−11.6
Creative Writing v3 EloChat & Writing21351907−11.5
FrontierMath Tiers 1-3 (v2) - PrivateMath85.674.4−11.2
Humanity's Last Exam DiamondGeneral QA44.833.7−11.1
SpeciEval (Pooled English Runs)Safety87.998.7+10.8
SpeciEval (Refusal-Aware Retries, Historical)Safety87.998.8+10.8
LMCAGeneral QA64.553.9−10.6
SnorkelLegalLegal26.436.5+10.1
Code MigrationCode57.547.4−10.1
Eval Connections One-Shot with TrapsGames74.084.0+10.0
HiL-Bench (Human-in-Loop Benchmark)Agents57.066.9+9.9
LMArena Agent Arena Net Improvement (Steering Burden)Agents7.22.2−9.5
NoCoT-Bench NCRI 15.2General QA11598.3−9.2
Extended NYT Connections 940 (Quadratic v1)Games94.385.1−9.2
ACCoRDGeneral QA83.875.1−8.8
CheatBenchSafety45.337.0+8.3
FrontierCode 2.0 (Artificial Analysis)Code31.223.1−8.0
CVDP (517-problem set)Code62.254.3−7.9
Artificial Analysis Intelligence Index v5.0.1Indexes44.236.6−7.5
RSI-Exam 0.1 (Full 88)Agents0.50.4−7.3
LiveBench 2.0Agents82.174.8−7.3
Harvey HLAB — Criteria Pass RateLegal87.794.7+7.0
GDPval Extended (Mercor held-out rubric score)Professional Work62.955.9−7.0
AA-LCR Extended (Mercor held-out)Search73.966.9−7.0
Humanity's Sixth SenseMultimodal30.537.4+6.9
EnterpriseBench: CoreCraftProfessional Work68.761.9−6.8
SnorkelFinance 2.0Finance & Accounting16.510.0−6.5
AutomationBench 1.0.6 (Zapier)Agents26.920.7−6.2
Excel Modeling BenchmarkFinance & Accounting73.667.4−6.1
AA-Omniscience IndexIndexes37.125.0−6.0
Chess Puzzles (task version 2.0)Games43.037.0−6.0
BuseyBench SVGMultimodal6.35.7−5.9
Arena Image-to-WebDevCode16641637−5.8
𝜏³-BankingAgents44.750.5+5.8
Ruby LLM Benchmarks — Program FixerCode79.874.1−5.7
MA-BenchProfessional Work56.261.8+5.6
Snorkel Digital Work IndexIndexes21.816.3−5.5
Artificial Analysis Coding Agent Index v1.5Indexes59.754.3−5.4
ChessBench AccuracyGames71.076.0+5.4
APEX-1 (Mercor, mean score)Professional Work68.673.9+5.3
Epoch Capabilities Index (ECI)Indexes164158−5.3
LMArena Agent Arena Praise vs ComplaintAgents12.21.7−5.2
CursorBench 4.0Code46.641.6−5.0
Shroombench (mushroom identification, top-1)Multimodal44.049.0+5.0
Bug Hunt BenchCode25.730.7+5.0
LMArena Code Arena WebDevCode16911655−4.7
NoCoT-Bench NCKI (kspine v3)General QA119113−4.6
LMArena Agent Arena SteerabilityAgents10.71.6−4.5
DeepSearchQA (F1 score)Search94.690.3−4.3
Tax Agent BenchFinance & Accounting76.772.4−4.2
micro1 PharmaBenchHealth & Medicine9.713.9+4.2
CadQueryEval (Corrected Geometry)Code80.084.0+4.0
GeneBench-Pro Public Release SubsetScience22.026.0+4.0
MedXpertQA MM Extended (Mercor held-out)Health & Medicine64.160.1−4.0
PCT Political Inconsistency (CAIS)Safety36.740.6−3.9
LMArena Agent Arena Bash ReliabilityAgents9.82.0−3.9
LMArena Agent Arena Bash RecoveryAgents13.66.1−3.7
GDP.pdfProfessional Work24.027.6+3.6
DAYJOB: FinanceFinance & Accounting11.314.8+3.5
Longform Creative WritingChat & Writing86.382.8−3.5
MedXpertQA MM (200-question set)Health & Medicine79.876.3−3.5
CritPt v2 (agentic, avg@5)Science71.468.0−3.4
SciCode 1.0.1 (Artificial Analysis)Code56.459.7+3.4
Artificial Analysis Progress Index v1Indexes334324−3.3
AA-Briefcase EloAgents16451589−3.2
LMArena Agent Arena Confirmed SuccessAgents10.23.7−3.2
CUA-benchAgents9.05.8−3.2
CritPt (avg@5)Science29.126.0−3.1
Creative Writing v3 Rubric ScoreChat & Writing16.315.6−3.1
Artificial Analysis Intelligence Index v4.3.2Indexes50.848.1−2.7
Terminal-Bench 2.1Code88.085.4−2.6
Vibe Code Bench v1.1Code88.485.9−2.5
Artificial Analysis Intelligence Index v4.3Indexes50.748.2−2.5
SWE-Marathon v1.1Code48.846.3−2.5
GDPval-AA v2Professional Work17081662−2.3
DeepSWE v1.1Code73.275.4+2.2
GDPval-AA v2.1Professional Work17291681−2.1
Bench to the Future 3 — September Panel — PooledForecasting0.10.1−2.1
Harvey LAB-AA v1.0 (criterion pass rate)Legal93.595.5+2.0
CharXiv Extended (Mercor held-out)Multimodal79.881.8+2.0
Realm Financial ReasoningFinance & Accounting47.445.5−1.9
Vision Arena OverallMultimodal12851291+1.6
Roboflow Vision Evals (September 2026 protocol)Multimodal78.379.8+1.5
Arena Alignment IndexSafety75.677.1+1.5
SWE-TogetherCode63.862.4−1.4
OSWorld 2.0 - reported partial reward, patch and step limit unspecifiedAgents68.366.9−1.4
MysteryMechanismScience37.436.0−1.4
DTBenchGeneral QA97.996.5−1.3
SnorkelUnderwrite 2.0Finance & Accounting18.319.6+1.3
AutomationBench-AA 1.0.6Agents56.657.9+1.3
SimpleBenchGeneral QA80.681.8+1.2
LMArena Text Arena EloChat & Writing14901496+1.1
SnorkelManufacturingProfessional Work9.410.5+1.1
DAXBench v2Code86.285.1−1.1
APEX-AccountingFinance & Accounting54.553.5−1.0
AA-LCR v1.1Search82.083.0+1.0
LMArena Agent Arena Steering BurdenAgents4.42.6−0.9
JobBench MainProfessional Work65.764.9−0.8
AutomationBench (Public Set)Agents50.349.6−0.7
CharXiv (descriptive and reasoning combined)Multimodal94.693.9−0.7
ForecastBench Tournament Overall Brier IndexForecasting66.665.9−0.7
ObviousBenchGeneral QA100.099.3−0.7
OSWorld 2.0 - reported binary completion, patch and step limit unspecifiedAgents31.432.0+0.6
DAYJOB: HealthcareHealth & Medicine8.47.8−0.6
MMMU-Pro Extended (Mercor held-out)Multimodal34.333.8−0.5
GPQA Diamond (Artificial Analysis avg@5)General QA93.794.1+0.4
SnorkelRevOpsProfessional Work12.212.6+0.4
dfbench Detection RecallCybersecurity47.847.4−0.4
OTIS Mock AIME 2024-2025Math98.999.2+0.3
HackerRank-BenchCode42.642.9+0.3
ForecastBench Preliminary Dataset Brier IndexForecasting62.061.9−0.1
LMArena Agent Arena Tool HallucinationAgents0.90.8−0.1
AIME 2025Math100.0100.00.0
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 - InsuranceLegal0.00.00.0
Harvey's Legal Agent Benchmark - Intellectual PropertyLegal0.00.00.0
Harvey's Legal Agent Benchmark - Litigation Dispute ResolutionLegal0.00.00.0
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
Legal Research BenchLegal55.355.30.0

Claude Opus 5vsMuse Spark 1.3normalised score marginsData Nov 15, 2026Data: Vals AI, Artificial Analysis, Arena and 54 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…