Atlas

Compare Models

Claude Opus 5.5 vs Muse Spark 1.3

Claude Opus 5.5 leads by 6.6 capability points (≈95% interval +4.2 to +9.0): a clear lead over Muse Spark 1.3 · P(higher) ≈ 100%

Wins 155 of 216 shared benchmarks (50 lost, 11 tied)

Capability vs. relative cost
Claude Opus 5.5Muse 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 5.5vsMuse Spark 1.3capability vs. relative costData Nov 15, 2026Village LLM Atlasatlas.village.dev

Benchmark wins155 – 50 · 216 shared, 11 tied

Comparing matching setups only (46 benchmarks excluded) · suites counted once
← Claude Opus 5.5Muse Spark 1.3 →

Claude Opus 5.5vsMuse Spark 1.3wins by categoryData Nov 15, 2026Data: Vals AI, Artificial Analysis, Mercor and 60 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 5.5.

KernelBench Mega Normalized (RTX PRO 6000)Code100.06.2−93.8
CheatBenchSafety7.286.5−79.3
VoxelBench Text RatingGames26131616−71.0
Harvey's Legal Agent Benchmark - Corporate GovernanceLegal0.060.0+60.0
Harvey's Legal Agent Benchmark - Data Privacy CybersecurityLegal0.060.0+60.0
BrokenArXiv 05/2026Math95.036.5−58.5
Terminal-Bench-Science 0.1Science61.93.8−58.1
BrokenArXiv 08/2026 (Native Harnesses)Math77.420.2−57.1
AA-PersonalityBench Slop indexChat & Writing20.075.3+55.8
HoneyBench v0.2 (hack rate)Safety31.683.6−51.9
AA-PersonalityBench Transparency indexChat & Writing90.541.0−50.0
FrontierMath Tier 4 (v2) - PrivateMath95.046.3−48.7
BrokenArXiv 06/2026Math100.053.2−46.8
Mystery Game PuzzlesGames71.025.0−46.0
KernelBench CUDA Normalized (RTX PRO 6000)Code76.330.3−45.9
FrontierCS 2Code58.312.5−45.8
Terminal-Bench 4.0 (Artificial Analysis)Code59.616.7−42.9
FrontierML ($200 wallet)Agents58.816.0−42.9
CAD ArenaAgents74.631.8−42.7
ProofBench v1.1Math100.058.0−42.0
Code2Video-AA EloCode15361019−41.9
RiemannBenchMath69.628.0−41.6
ArXivMath 08/2026 (Native Harnesses)Math86.045.6−40.3
MatFlowBench Pass@1Science56.716.7−40.0
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
FrontierSWE V2 Worst@5Code52.012.6−39.4
Decision-Bench v1.1Professional Work59.119.8−39.3
Terminal-Bench 4.0Code64.827.8−37.1
TaxCalcBench TY25Finance & Accounting42.06.0−36.0
LLM Creative Story WritingChat & Writing3.70.6−35.7
Hedge-BenchFinance & Accounting44.29.1−35.1
Terminal-Bench Science 0.1 (Vals)Science48.614.3−34.3
LMArena Agent Arena Net Improvement (Steering Burden)Agents19.52.2−32.7
Web Clone BenchCode34.21.5−32.7
RuneBenchGames6.64.6−31.4
DAYJOB: Data ScienceProfessional Work37.36.0−31.3
SAFE-Teen 106 worst branch: Relationships (no prompt)Safety25.356.2−30.9
FrontierSWE V2 Best@5Code71.540.9−30.6
SAFE-Teen 106 worst branch: Health Advice (no prompt)Safety44.313.9+30.4
Chess Puzzles (task version 2.0)Games67.037.0−30.0
APEX-SWECode67.639.1−28.5
SAFE-Teen 106: Health Advice (no prompt)Safety35.06.7+28.3
sudo L7Code41.713.9−27.8
ALE-BenchCode27481981−27.2
SWE-bench Multimodal (Vals v1, 480 Tasks)Code70.243.1−27.1
GameBench 2Games94.868.5−26.3
AA-3D v1.0 EloCode12021032−24.8
TextQuests Game ProgressGames57.333.0−24.4
MineBench — Bradley-Terry RatingGames21341747−23.4
Medical Long Context Reasoning (MLCR-AA)Health & Medicine66.743.3−23.3
FrontierCode 2.0 (Artificial Analysis)Code46.423.1−23.3
SAFE-Teen 106 worst branch: Health Advice (under-18 prompt)Safety27.74.5+23.2
AutoResearchExam (hidden-test AUARC)Agents0.60.4−23.0
SAFE-Teen 106: Relationships (no prompt)Safety12.234.4−22.1
GBENCH One-shot Coding GScoreGames73.952.7−21.2
Humanity's Last Exam DiamondGeneral QA54.633.7−20.9
LMArena Code Arena WebDevCode18141655−20.8
APEX-Agents 1.1Professional Work81.361.3−20.0
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 - Corporate M&ALegal0.020.0+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 - Structured Finance SecuritizationLegal0.020.0+20.0
Harvey's Legal Agent Benchmark - Trusts Estates Private ClientLegal0.020.0+20.0
GDPval Extended (Mercor held-out rubric score)Professional Work75.855.9−19.9
LMArena Agent Arena Praise vs ComplaintAgents40.31.7−19.3
AA-PersonalityBench Expressiveness indexChat & Writing90.571.4−19.2
Harvey HLAB — Criteria Pass RateLegal75.894.7+19.0
AA-AnalystAgent (pass^5)Professional Work56.337.5−18.7
Vals RSI Index v1.1 (historical five tasks)Agents37.118.7−18.5
HANDBOOK.md Agents v1.1Professional Work52.333.9−18.4
DeepFinanceFinance & Accounting54.837.0−17.8
Vals RSI Index v1.1 (four tasks)Agents37.319.6−17.7
MMMU-Pro Extended (Mercor held-out)Multimodal51.033.8−17.2
DAYJOB: HealthcareHealth & Medicine24.77.8−16.9
FrontierMath Tiers 1-3 (v2) - PrivateMath91.274.4−16.8
DAYJOB: AccountingFinance & Accounting34.418.0−16.4
CursorBench 4.0Code57.841.6−16.2
Conceptual Reasoning IndexIndexes77.966.2−16.1
CadQueryEval (Corrected Geometry)Code100.084.0−16.0
LLM Debate BenchmarkChat & Writing17011593−15.4
Snorkel Agentic Coding 2.0Code40.425.0−15.4
AA-PersonalityBench Organization indexChat & Writing79.163.8−15.4
SAFE-Teen 106: Health Advice (under-18 prompt)Safety17.32.1+15.2
Gray Swan IPI Attack Success (k=15)Safety1.015.9−14.9
RSI-Exam 0.1 (Full 88)Agents0.50.4−14.5
Snorkel SWE-bench CLICode16.62.2−14.4
LMCAGeneral QA68.253.9−14.4
Westworld Finance Diligence BenchFinance & Accounting59.445.2−14.2
Professional Reasoning Benchmark - LegalLegal47.661.6+14.0
CritPt v2 (agentic, avg@5)Science81.768.0−13.7
ACCoRDGeneral QA88.475.1−13.3
Olam Social Poker EloGames15061494−13.0
EnterpriseBench: CoreCraftProfessional Work74.461.9−12.5
Design Creativity BenchCode51.047.2−12.1
AA-Briefcase v1.1 EloAgents18011581−12.0
SWE-bench Verified Extended (Mercor held-out)Code66.054.0−12.0
CWE-bench v1 Programmatic Pass@1Cybersecurity67.055.0−12.0
LiveBench 2.0Agents86.574.8−11.8
Artificial Analysis Coding Agent Index v1.5Indexes66.054.3−11.7
PCT Political Inconsistency (CAIS)Safety29.140.6−11.5
AA-PersonalityBench Warmth indexChat & Writing84.896.2+11.5
SpeciEval (Refusal-Aware Retries, Historical)Safety87.298.8+11.5
SpeciEval (Pooled English Runs)Safety87.298.7+11.5
FrontierCode 1.1 Main (Artificial Analysis)Code52.240.6−11.5
BuseyBench SVGMultimodal6.85.7−11.4
HardGeoBench Avg DistanceMultimodal6551022−11.3
ChessBench CoherenceGames80.191.2+11.1
MedXpertQA MM Extended (Mercor held-out)Health & Medicine71.260.1−11.1
AA-Omniscience IndexIndexes46.425.0−10.7
DAXBench v2Code95.785.1−10.6
CVDP (517-problem set)Code64.154.3−9.8
AA-PersonalityBench Informativeness indexChat & Writing90.5100+9.6
MedXpertQA MM (200-question set)Health & Medicine85.776.3−9.4
DistressBenchSafety75.684.9+9.3
DAYJOB: FinanceFinance & Accounting23.914.8−9.1
Bug Hunt BenchCode39.730.7−9.0
Humanity's Last Exam (Text-Only)General QA57.548.7−8.8
ChessBench EloGames13491201−8.8
HardGeoBench Country AccuracyMultimodal68.860.0−8.7
Epoch Capabilities Index (ECI)Indexes169158−8.6
SnorkelFinance 2.0Finance & Accounting18.610.0−8.6
Excel Modeling BenchmarkFinance & Accounting75.967.4−8.5
LMArena Agent Arena Confirmed SuccessAgents20.73.7−8.5
HackerRank-BenchCode51.242.9−8.4
ArXivMath 05/2026Math81.773.3−8.3
APEX-AccountingFinance & Accounting61.853.5−8.3
CUA-benchAgents14.05.8−8.2
GDPval-AA v2.1Professional Work18661681−8.2
Ramp Accounting BenchFinance & Accounting50.542.5−8.1
WellnessBenchSafety53.061.0+8.0
LMArena Agent Arena Steering BurdenAgents18.62.6−8.0
HiL-Bench (Human-in-Loop Benchmark)Agents59.066.9+7.9
GDP.xlsxProfessional Work30.322.6−7.7
AA-PersonalityBench Conviction indexChat & Writing69.577.2+7.7
dfbench Detection RecallCybersecurity54.947.4−7.5
HardGeoBench <=100miMultimodal62.555.0−7.5
Snorkel Digital Work IndexIndexes23.616.3−7.3
AA-LCR Extended (Mercor held-out)Search74.266.9−7.3
Creative Writing v3 EloChat & Writing20511907−7.3
APEX-1 (Mercor, mean score)Professional Work65.873.0+7.2
Humanity's Sixth SenseMultimodal44.637.4−7.2
SciCode 1.0.1 (Artificial Analysis)Code66.959.7−7.2
Immigration BenchLegal72.165.0−7.1
SimpleBenchGeneral QA88.481.8−6.6
ArXivMath 06/2026Math83.376.7−6.6
LMArena Agent Arena Bash ReliabilityAgents15.12.0−6.6
SWE-TogetherCode68.862.4−6.4
LegalReasonBenchLegal46.540.4−6.1
Arena Alignment IndexSafety83.277.1−6.1
CritPt (avg@5)Science31.726.0−5.7
Roboflow Vision Evals (September 2026 protocol)Multimodal85.579.8−5.7
DAYJOB: TaxFinance & Accounting9.23.6−5.6
Terminal-Bench 2.1Code83.588.8+5.3
Financial Coaching BenchFinance & Accounting76.271.0−5.2
SnorkelLegalLegal31.436.5+5.1
HardGeoBench <=10miMultimodal43.838.8−5.0
ITBench-AAAgents38.233.2−5.0
Harvey LAB-AA v1.1 (hallucination-gated)Legal4.28.9+4.7
LMArena Agent Arena Bash RecoveryAgents15.06.1−4.5
Harvey LAB-AA v1.0 (criterion pass rate)Legal91.295.5+4.2
Harvey LAB (Mercor run, undisclosed ~213-task cohort)Legal10.815.0+4.2
GeneBench-Pro Public Release SubsetScience30.026.0−4.0
AA-PersonalityBench Imagination indexChat & Writing94.398.1+3.8
MentalHealthBenchSafety52.448.6−3.8
SAFE-Teen 106: Urgent Safety (no prompt)Safety12.79.0+3.7
ChessBench AccuracyGames79.376.0−3.5
Ruby LLM Benchmarks — Program FixerCode77.574.1−3.5
Extended NYT Connections 940 (Quadratic v1)Games88.585.1−3.4
micro1 PharmaBenchHealth & Medicine10.813.9+3.1
SnorkelUnderwrite 2.0Finance & Accounting22.719.6−3.1
CharXiv Extended (Mercor held-out)Multimodal84.781.8−2.9
τ³-Banking (Mercor run, bm25_grep retrieval)Agents55.052.2−2.8
CharXiv (descriptive and reasoning combined)Multimodal96.493.9−2.5
DTBenchGeneral QA98.996.5−2.4
DAYJOB: LawLegal25.122.8−2.3
Visa Agentic Commerce BenchmarkAgents62.264.4+2.2
GDP.pdf (Artificial Analysis, All-pass)Professional Work28.826.6−2.2
ComplexConstraintsChat & Writing49.951.9+2.0
Eval Connections One-Shot with TrapsGames86.084.0−2.0
Longform Creative WritingChat & Writing84.682.8−1.8
LMArena Text Arena EloChat & Writing15061496−1.7
Creative Writing v3 Rubric ScoreChat & Writing16.015.6−1.7
AA-LCR v1.1Search84.783.0−1.7
Access to Justice BenchmarkLegal73.872.2−1.6
Finance Agent v2Finance & Accounting58.660.0+1.4
DeepSWE v1.1Code74.275.4+1.2
SAFE-Teen 106 worst branch: Urgent Safety (no prompt)Safety26.525.6+0.9
SAFE-Teen 106 worst branch: Relationships (under-18 prompt)Safety2.43.2−0.9
OTIS Mock AIME 2024-2025Math100.099.2−0.8
SAFE-Teen 106 worst branch: Urgent Safety (under-18 prompt)Safety10.511.3−0.8
ObviousBenchGeneral QA100.099.3−0.7
SAFE-Teen 106: Urgent Safety (under-18 prompt)Safety3.12.7+0.4
ForecastBench Preliminary Dataset Brier IndexForecasting62.261.9−0.3
SAFE-Teen 106: Relationships (under-18 prompt)Safety0.40.6−0.1
SnorkelManufacturingProfessional Work10.410.5+0.1
SnorkelRevOpsProfessional Work12.512.6+0.1
LMArena Agent Arena Tool HallucinationAgents0.70.80.0
AIME 2025Math100.0100.00.0
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 - TaxLegal0.00.00.0
Harvey's Legal Agent Benchmark - White Collar Defense InvestigationsLegal0.00.00.0
Legacy-Bench (Fireworks, avg@3)Code62.062.00.0
SWE-Marathon v1.1Code46.346.30.0

Claude Opus 5.5vsMuse Spark 1.3normalised score marginsData Nov 15, 2026Data: Vals AI, Artificial Analysis, Mercor and 60 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…