Atlas

Compare Models

Hy4 vs Muse Ember

Muse Ember leads by 0.3 capability points (≈95% interval −2.3 to +2.9): statistically tied · P(higher) ≈ 59%

Wins 8 of 15 shared benchmarks (7 lost)

Capability vs. relative cost
Hy4Muse EmberClosed weightsOpen weights

Hy4 has no setting with a relative cost yet.

Benchmark wins7 – 8 · 15 shared

Comparing matching setups only (157 benchmarks excluded) · suites counted once
← Hy4Muse Ember →
Data: Surge AI, Mercor, DAXBench and 3 othersatlas.village.dev

Margins

Each benchmark scaled 0–100% (its declared range, else the field’s range); Δ is Muse Ember minus Hy4.

FoodTruck BenchBusiness simulations6759834639−42.3
Chartography (November 2026 rescoring)Perception & media › Documents & charts49.279.3+30.1
DAXBench v2Software › Data & ML87.262.8−24.5
DAYJOB: Finance (October 2026 rescoring)Professional › Finance, accounting & tax9.224.2+15.0
Humanity's Last Exam DiamondKnowledge & reasoning › General knowledge32.722.0−10.7
DAYJOB: Healthcare (October 2026 rescoring)Health & medicine7.217.2+10.0
APEX-Agents 1.1Professional › General knowledge work85.175.7−9.4
Harvey LAB (Mercor run, undisclosed ~213-task cohort)Professional › Legal13.622.7+9.1
ComplexConstraints (November 2026 rescoring)Language & writing › Instruction following66.858.8−8.0
EnterpriseBench: CoreCraftTool & computer use › Customer service & operations68.262.1−6.1
HANDBOOK.md Agents v1.1Tool & computer use › Customer service & operations23.729.8+6.1
GDP.pdf (November 2026 rescoring)Professional › General knowledge work43.649.2+5.6
τ³-Banking (Mercor run, bm25_grep retrieval)Tool & computer use › Customer service & operations48.153.3+5.2
RiemannBench (November 2026 rescoring)Math51.253.6+2.4
GDP.xlsxProfessional › General knowledge work17.715.4−2.3
Data: Surge AI, Mercor, DAXBench and 3 othersatlas.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…