Atlas

Compare Models

Muse Spark 1.3 vs Qwen3.8-Max

Muse Spark 1.3 leads by 1.5 capability points (≈95% interval −0.8 to +3.9): statistically tied · P(higher) ≈ 90%

Wins 26 of 28 shared benchmarks (2 lost)

Capability vs. relative cost
Muse Spark 1.3Qwen3.8-MaxClosed 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-Maxcapability vs. relative costData Nov 15, 2026Village LLM Atlasatlas.village.dev

Benchmark wins26 – 2 · 28 shared

Comparing matching setups only (239 benchmarks excluded) · suites counted once
← Muse Spark 1.3Qwen3.8-Max →

Muse Spark 1.3vsQwen3.8-Maxwins by categoryData Nov 15, 2026Data: Artificial Analysis, Conceptual Reasoning Benchmark Authors, AIMING Lab (UNC-Chapel Hill) and 6 othersVillage LLM Atlasatlas.village.dev

Margins

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

Medical Long Context Reasoning (MLCR-AA)Health & Medicine43.319.4−23.9
GameBench 2Games68.551.4−17.1
Terminal-Bench 4.0 (Artificial Analysis)Code33.318.7−14.6
BabaIsBench Stage 0: The IntroGames46.058.0+12.0
AA-Briefcase EloAgents15891388−11.7
AA-Omniscience IndexIndexes25.03.4−10.8
Conceptual Reasoning IndexIndexes66.259.4−9.4
AutomationBench-AA 1.0.6Agents57.949.2−8.6
Artificial Analysis Intelligence Index v4.3.2Indexes48.140.2−7.9
Artificial Analysis Intelligence Index v4.3Indexes48.240.3−7.9
LMCAGeneral QA53.946.2−7.6
Terminal-Bench 2.1Code88.881.3−7.5
RSI-Exam 0.1 (Full 88)Agents0.40.3−6.9
SciCode 1.0.1 (Artificial Analysis)Code59.753.2−6.5
GDP.pdf (Artificial Analysis, All-pass)Professional Work26.620.2−6.4
CritPt (avg@5)Science26.020.0−6.0
Humanity's Last Exam (Text-Only)General QA48.743.0−5.7
AA-LCR v1.1Search83.078.3−4.7
DTBenchGeneral QA96.592.0−4.5
ACCoRDGeneral QA75.171.4−3.7
GDPval-AA v2.1Professional Work16811611−3.1
BuseyBench SVGMultimodal5.75.4−2.9
Artificial Analysis Progress Index v1Indexes324320−1.7
GDPval-AA v2Professional Work16621630−1.6
GPQA Diamond (Artificial Analysis avg@5)General QA94.192.7−1.4
Ramp Accounting BenchFinance & Accounting42.541.2−1.3
𝜏³-BankingAgents50.551.3+0.8
Epoch Capabilities Index (ECI)Indexes158157−0.4

Muse Spark 1.3vsQwen3.8-Maxnormalised score marginsData Nov 15, 2026Data: Artificial Analysis, Conceptual Reasoning Benchmark Authors, AIMING Lab (UNC-Chapel Hill) and 6 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…