Muse Ember vs Muse Wonder
TryTop 2 now
Muse Wonder leads by 1.3 capability points (≈95% interval −1.1 to +3.7): statistically tied · P(higher) ≈ 85%
Wins 51 of 65 shared benchmarks (14 lost)
Capability vs. relative cost
Muse EmberMuse WonderClosed weightsOpen weights
Benchmark wins14 – 51 · 65 shared
Comparing matching setups only (1 benchmark excluded) · suites counted once
Area← Muse EmberMuse Wonder →
Data: Artificial Analysis, Vals AI, Surge AI and 11 othersatlas.village.dev
Margins
Each benchmark scaled 0–100% (its declared range, else the field’s range); Δ is Muse Wonder minus Muse Ember.
| Code Migration v1.1 (Vals Index v2.2 subset) | Software › Software engineering | 47.1 | 69.8 | +22.7 |
| TaxCalcBench TY25 | Professional › Finance, accounting & tax | 2.0 | 24.0 | +22.0 |
| DAXBench v2 | Software › Data & ML | 62.8 | 84.0 | +21.3 |
| DAYJOB: Finance (October 2026 rescoring) | Professional › Finance, accounting & tax | 24.2 | 38.8 | +14.6 |
| DAYJOB: Healthcare (October 2026 rescoring) | Health & medicine | 17.2 | 31.2 | +14.0 |
| Humanity's Last Exam Diamond | Knowledge & reasoning › General knowledge | 25.1 | 39.0 | +13.9 |
| BuseyBench SVG | Perception & media › Generation | 5.4 | 6.6 | +12.0 |
| Terminal-Bench 4.0 | Software › Software engineering | 39.4 | 49.5 | +10.1 |
| ComplexConstraints (November 2026 rescoring) | Language & writing › Instruction following | 58.8 | 67.9 | +9.1 |
| CritPt v2 (agentic, avg@5) | Science › Physical sciences | 62.3 | 71.1 | +8.9 |
| SWE Atlas v1.1 - Overall | Software › Software engineering | 56.0 | 64.8 | +8.8 |
| AA-Omniscience v1.1 Index | Knowledge & reasoning › General knowledge | 7.7 | 25.1 | +8.7 |
| Artificial Analysis Economics Index | Composite indexes | 41.0 | 49.5 | +8.6 |
| Artificial Analysis Legal Index | Professional › Legal | 38.5 | 46.9 | +8.4 |
| GDP.pdf (Artificial Analysis, All-pass) | Professional › General knowledge work | 22.8 | 30.6 | +7.8 |
| Artificial Analysis Engineering Index | Science › Engineering | 41.8 | 49.6 | +7.8 |
| DeepFinance | Professional › Finance, accounting & tax | 36.5 | 44.2 | +7.7 |
| AA-Briefcase v1.1 Elo | Professional › General knowledge work | 1520 | 1659 | +7.6 |
| Artificial Analysis Intelligence Index v5.0.1 | Composite indexes | 36.0 | 43.6 | +7.6 |
| Artificial Analysis Healthcare & Medical Index | Health & medicine | 41.3 | 48.7 | +7.4 |
| Ramp SWE-Bench v2 | Software › Software engineering | 51.8 | 58.6 | +6.8 |
| Artificial Analysis Finance & Accounting Index | Professional › Finance, accounting & tax | 44.6 | 51.1 | +6.6 |
| GDP.xlsx | Professional › General knowledge work | 15.4 | 21.8 | +6.4 |
| Artificial Analysis Coding Agent Index v2.0 | Software › Software engineering | 45.9 | 52.0 | +6.0 |
| Artificial Analysis Strategy & Ops Index | Professional › General knowledge work | 48.7 | 54.5 | +5.8 |
| Terminal-Bench-Science 0.1 | Science › Multidisciplinary | 20.0 | 25.7 | +5.7 |
| HiL-Bench (Human-in-Loop Benchmark) | Tool & computer use › General agents | 74.0 | 79.7 | +5.7 |
| RiemannBench (November 2026 rescoring) | Math | 53.6 | 59.2 | +5.6 |
| GDP.pdf (November 2026 rescoring) | Professional › General knowledge work | 49.2 | 54.8 | +5.6 |
| LMArena Code Arena WebDev | Software › Frontend & design | 1608 | 1648 | +5.3 |
| FrontierCUA v1 pass@1 | Tool & computer use › Computer & browser use | 7.5 | 12.5 | +5.0 |
| Artificial Analysis Coding Agent Index v2.1 | Software › Software engineering | 39.7 | 44.5 | +4.8 |
| APEX-1 (Mercor, mean score) | Professional › General knowledge work | 70.4 | 75.1 | +4.7 |
| Vals Index v2.2 | Composite indexes | 60.5 | 64.9 | +4.4 |
| Medical Long Context Reasoning (MLCR-AA, October 2026 methodology) | Health & medicine | 18.3 | 22.2 | +3.9 |
| OSWorld 2.1 full - reported partial reward, step limit unspecified | Tool & computer use › Computer & browser use | 69.5 | 72.6 | +3.1 |
| Professional Reasoning Benchmark - Legal | Professional › Legal | 55.6 | 58.4 | +2.8 |
| Professional Reasoning Benchmark - Finance | Professional › Finance, accounting & tax | 56.0 | 58.7 | +2.7 |
| Terminal-Bench 4.0 (Artificial Analysis) | Software › Software engineering | 40.9 | 38.4 | −2.5 |
| Artificial Analysis Progress Index v1 | Composite indexes | 329 | 336 | +2.5 |
| LMArena Agent Arena Confirmed Success | Tool & computer use › General agents | -2.0 | 2.5 | +2.2 |
| GBENCH One-shot Coding GScore | Games | 56.4 | 58.5 | +2.1 |
| FORTRESS Average Risk Score (ARS) | Safety & alignment | 11.9 | 13.8 | −1.8 |
| Finance Agent v2.1 | Professional › Finance, accounting & tax | 63.8 | 65.5 | +1.7 |
| APEX-SWE | Software › Software engineering | 52.9 | 54.6 | +1.7 |
| LMArena Agent Arena Steering Burden | Tool & computer use › General agents | 4.8 | 1.5 | −1.6 |
| LMArena Agent Arena Bash Reliability | Tool & computer use › General agents | 6.6 | 3.4 | −1.6 |
| Legal Research Bench | Professional › Legal | 49.0 | 50.5 | +1.4 |
| τ³-Banking (Mercor run, bm25_grep retrieval) | Tool & computer use › Customer service & operations | 53.3 | 51.9 | −1.4 |
| APEX-Agents 1.1 | Professional › General knowledge work | 75.7 | 77.0 | +1.3 |
| HLAB-Vals-1.1 | Professional › Legal | 25.0 | 23.8 | −1.2 |
| LMArena Agent Arena Net Improvement (Steering Burden) | Tool & computer use › General agents | 1.0 | 0.6 | −0.7 |
| FrontierCode 2.0 (Artificial Analysis) | Software › Software engineering | 27.2 | 27.9 | +0.7 |
| Vibe Code Bench v1.1 | Software › Frontend & design | 83.7 | 83.1 | −0.6 |
| EnterpriseBench: CoreCraft | Tool & computer use › Customer service & operations | 62.1 | 61.5 | −0.6 |
| LMArena Agent Arena Tool Hallucination | Tool & computer use › Tool calling | 0.9 | -0.2 | −0.5 |
| OSWorld 2.1 full - reported binary completion, step limit unspecified | Tool & computer use › Computer & browser use | 33.8 | 34.3 | +0.5 |
| Vals Legal Index | Professional › Legal | 75.7 | 75.3 | −0.4 |
| Excel Modeling Benchmark v1.1 | Professional › Finance, accounting & tax | 72.2 | 72.5 | +0.3 |
| Vals Finance Index | Professional › Finance, accounting & tax | 60.9 | 61.2 | +0.3 |
| Harvey LAB (Mercor run, undisclosed ~213-task cohort) | Professional › Legal | 22.7 | 23.0 | +0.3 |
| HANDBOOK.md Agents v1.1 | Tool & computer use › Customer service & operations | 29.8 | 29.5 | −0.3 |
| Tax Agent Bench | Professional › Finance, accounting & tax | 71.4 | 71.2 | −0.2 |
| LMArena Agent Arena Praise vs Complaint | Tool & computer use › General agents | -2.7 | -3.0 | −0.1 |
| AutomationBench-AA 1.0.6 | Tool & computer use › Customer service & operations | 68.1 | 68.1 | 0.0 |
Data: Artificial Analysis, Vals AI, Surge AI and 11 othersatlas.village.dev