Atlas

Compare Models

Muse Spark 1.3 vs Qwen3.8 Max (0902)

Muse Spark 1.3 leads by 0.9 capability points (≈95% interval −1.4 to +3.1): statistically tied · P(higher) ≈ 77%

Wins 33 of 46 shared benchmarks (13 lost)

Capability vs. relative cost
Muse Spark 1.3Qwen3.8 Max (0902)Closed 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.

Muse Spark 1.3vsQwen3.8 Max (0902)capability vs. relative costData Nov 15, 2026Village LLM Atlasatlas.village.dev

Benchmark wins33 – 13 · 46 shared

Comparing matching setups only (79 benchmarks excluded) · suites counted once
← Muse Spark 1.3Qwen3.8 Max (0902) →

Muse Spark 1.3vsQwen3.8 Max (0902)wins by categoryData Nov 15, 2026Data: Artificial Analysis, AIMING Lab (UNC-Chapel Hill), BuseyBench and 8 othersVillage LLM Atlasatlas.village.dev

Margins

Each benchmark scaled 0–100% (its declared range, else the field’s range); Δ is Qwen3.8 Max (0902) minus Muse Spark 1.3.

AA-PersonalityBench Informativeness indexChat & Writing10039.1−61.5
AA-PersonalityBench Imagination indexChat & Writing98.148.6−50.0
AA-PersonalityBench Expressiveness indexChat & Writing71.423.8−48.1
AA-PersonalityBench Warmth indexChat & Writing96.248.6−48.1
AA-PersonalityBench Conviction indexChat & Writing77.235.3−42.3
Medical Long Context Reasoning (MLCR-AA)Health & Medicine43.320.0−23.3
CritPt v2 (agentic, avg@5)Science68.051.4−16.6
AA-3D v1.0 EloCode1032954−11.3
Humanity's Last Exam DiamondGeneral QA33.724.0−9.7
CritPt (avg@5)Science26.017.7−8.3
FrontierSWE V2Code25.817.8−8.0
AA-PersonalityBench Organization indexChat & Writing63.871.4+7.7
SciCode 1.0.1 (Artificial Analysis)Code59.752.1−7.6
AA-AnalystAgent (pass^5)Professional Work37.545.0+7.5
ITBench-AAAgents33.240.3+7.0
AA-Omniscience IndexIndexes25.012.0−6.5
Last Translation Benchmark (LTBv1-eval, blind)Chat & Writing18.412.5−5.9
Humanity's Last Exam (Text-Only)General QA48.743.1−5.6
Terminal-Bench 4.0 (Artificial Analysis)Code33.338.9+5.6
Visa Agentic Commerce BenchmarkAgents64.460.0−4.4
AA-PersonalityBench Transparency indexChat & Writing41.044.8+3.8
GDP.pdf (Artificial Analysis, All-pass)Professional Work26.622.8−3.8
Artificial Analysis Intelligence Index v5.0.1Indexes36.633.7−3.0
Artificial Analysis Intelligence Index v5.0Indexes36.433.6−2.9
Artificial Analysis Intelligence Index v4.3Indexes48.245.4−2.7
𝜏³-BankingAgents50.547.8−2.7
Artificial Analysis Intelligence Index v4.3.2Indexes48.145.4−2.7
AA-LCR v1.1Search83.080.3−2.7
FrontierCode 1.1 Main (Artificial Analysis)Code40.643.2+2.5
DAXBench v2Code85.183.0−2.1
AA-PersonalityBench Slop indexChat & Writing75.373.3−1.9
AA-Briefcase EloAgents15891622+1.9
Harvey LAB-AA v1.0 (criterion pass rate)Legal95.593.6−1.8
Epoch Capabilities Index (ECI)Indexes158156−1.7
AutomationBench-AA 1.0.6Agents57.956.2−1.7
GPQA Diamond (Artificial Analysis avg@5)General QA94.192.8−1.3
GDPval-AA v2Professional Work16621689+1.3
Terminal-Bench-Science 0.1Science11.011.9+1.0
Terminal-Bench 4.0Code27.827.0−0.8
BuseyBench SVGMultimodal5.75.8+0.8
FrontierCode 2.0 (Artificial Analysis)Code23.123.4+0.3
GDPval-AA v2.1Professional Work16811674−0.3
Artificial Analysis Progress Index v1Indexes324324−0.3
Code2Video-AA EloCode10191021+0.2
RSI-Exam 0.1 (Full 88)Agents0.40.4+0.2
Terminal-Bench 2.1Code88.888.80.0

Muse Spark 1.3vsQwen3.8 Max (0902)normalised score marginsData Nov 15, 2026Data: Artificial Analysis, AIMING Lab (UNC-Chapel Hill), BuseyBench and 8 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…