Muse Wonder vs Qwen4-Max
Qwen4-Max leads by 0.2 capability points (≈95% interval −2.2 to +2.7): statistically tied · P(higher) ≈ 57%
Wins 26 of 51 shared benchmarks (24 lost, 1 tied)
Capability vs. relative cost
Muse WonderQwen4-MaxClosed weightsOpen weights
Benchmark wins24 – 26 · 51 shared, 1 tied
Comparing matching setups only (4 benchmarks excluded) · suites counted once
Area← Muse WonderQwen4-Max →
Data: Artificial Analysis, Surge AI, Vals AI and 5 othersatlas.village.dev
Margins
Each benchmark scaled 0–100% (its declared range, else the field’s range); Δ is Qwen4-Max minus Muse Wonder.
| KradleBench | Games | 27.6 | 11.0 | −16.6 |
| LMArena Code Arena WebDev | Software › Frontend & design | 1648 | 1750 | +13.6 |
| DAYJOB: Finance (October 2026 rescoring) | Professional › Finance, accounting & tax | 38.8 | 25.3 | −13.5 |
| LMArena Agent Arena Net Improvement (Steering Burden) | Tool & computer use › General agents | 0.6 | 7.3 | +13.0 |
| Code Migration v1.1 (Vals Index v2.2 subset) | Software › Software engineering | 69.8 | 57.3 | −12.5 |
| GDP.pdf (November 2026 rescoring) | Professional › General knowledge work | 54.8 | 43.6 | −11.2 |
| Terminal-Bench 4.0 (Artificial Analysis) | Software › Software engineering | 38.4 | 48.5 | +10.1 |
| HANDBOOK.md Agents v1.1 | Tool & computer use › Customer service & operations | 29.5 | 39.4 | +9.9 |
| Legal Research Bench | Professional › Legal | 50.5 | 41.3 | −9.1 |
| ComplexConstraints (November 2026 rescoring) | Language & writing › Instruction following | 67.9 | 59.1 | −8.8 |
| DAYJOB: Accounting | Professional › Finance, accounting & tax | 30.8 | 22.4 | −8.4 |
| LMArena Agent Arena Praise vs Complaint | Tool & computer use › General agents | -3.0 | 13.0 | +8.0 |
| EnterpriseBench: CoreCraft | Tool & computer use › Customer service & operations | 61.5 | 68.7 | +7.2 |
| DAYJOB: Healthcare (October 2026 rescoring) | Health & medicine | 31.2 | 24.4 | −6.8 |
| LLM Debate Benchmark | Language & writing › Language & wordplay | 1637 | 1679 | +5.9 |
| Humanity's Last Exam Diamond | Knowledge & reasoning › General knowledge | 39.0 | 44.9 | +5.9 |
| CritPt v2 (agentic, avg@5) | Science › Physical sciences | 71.1 | 66.0 | −5.1 |
| Vals Legal Index | Professional › Legal | 75.3 | 70.7 | −4.5 |
| AutomationBench-AA 1.0.6 | Tool & computer use › Customer service & operations | 68.1 | 72.6 | +4.5 |
| GDP.pdf (Artificial Analysis, All-pass) | Professional › General knowledge work | 30.6 | 26.2 | −4.4 |
| Vibe Code Bench v1.1 | Software › Frontend & design | 83.1 | 86.7 | +3.6 |
| LMArena Agent Arena Steering Burden | Tool & computer use › General agents | 1.5 | 8.0 | +3.3 |
| LMArena Agent Arena Confirmed Success | Tool & computer use › General agents | 2.5 | 8.8 | +3.2 |
| DAYJOB: Law (November 2026 release) | Professional › Legal | 20.6 | 17.5 | −3.1 |
| Artificial Analysis Finance & Accounting Index | Professional › Finance, accounting & tax | 51.1 | 54.1 | +3.0 |
| DAYJOB: Tax | Professional › Finance, accounting & tax | 6.0 | 8.8 | +2.8 |
| Medical Long Context Reasoning (MLCR-AA, October 2026 methodology) | Health & medicine | 22.2 | 19.4 | −2.8 |
| Artificial Analysis Legal Index | Professional › Legal | 46.9 | 49.6 | +2.7 |
| HLAB-Vals-1.1 | Professional › Legal | 23.8 | 21.3 | −2.5 |
| Terminal-Bench-Science 0.1 | Science › Multidisciplinary | 25.7 | 23.3 | −2.4 |
| Artificial Analysis Strategy & Ops Index | Professional › General knowledge work | 54.5 | 56.9 | +2.4 |
| LiveBench 2.0 (2026-11-06 release) | Composite indexes | 70.7 | 73.1 | +2.4 |
| GDP.xlsx | Professional › General knowledge work | 21.8 | 23.7 | +1.9 |
| Artificial Analysis Economics Index | Composite indexes | 49.5 | 51.3 | +1.8 |
| GDPval-AA v2.1 | Professional › General knowledge work | 1770 | 1809 | +1.7 |
| Vals Index v2.2 | Composite indexes | 64.9 | 63.2 | −1.7 |
| Excel Modeling Benchmark v1.1 | Professional › Finance, accounting & tax | 72.5 | 70.8 | −1.7 |
| AA-Briefcase v1.1 Elo | Professional › General knowledge work | 1659 | 1686 | +1.5 |
| FrontierCode 2.0 (Artificial Analysis) | Software › Software engineering | 27.9 | 26.5 | −1.4 |
| AA-Omniscience v1.1 Index | Knowledge & reasoning › General knowledge | 25.1 | 27.7 | +1.3 |
| Finance Agent v2.1 | Professional › Finance, accounting & tax | 65.5 | 66.7 | +1.1 |
| Tax Agent Bench | Professional › Finance, accounting & tax | 71.2 | 70.0 | −1.1 |
| Terminal-Bench 4.0 | Software › Software engineering | 49.5 | 48.5 | −1.0 |
| Vals Finance Index | Professional › Finance, accounting & tax | 61.2 | 62.0 | +0.8 |
| Artificial Analysis Intelligence Index v5.0.1 | Composite indexes | 43.6 | 42.9 | −0.7 |
| LMArena Agent Arena Tool Hallucination | Tool & computer use › Tool calling | -0.2 | 1.2 | +0.7 |
| Artificial Analysis Engineering Index | Science › Engineering | 49.6 | 50.1 | +0.5 |
| sudo L7 (October 2026 rescoring) | Software › Software engineering | 16.1 | 15.6 | −0.5 |
| Artificial Analysis Healthcare & Medical Index | Health & medicine | 48.7 | 48.2 | −0.5 |
| LMArena Agent Arena Bash Reliability | Tool & computer use › General agents | 3.4 | 3.4 | 0.0 |
| DualEntry Accounting AI Benchmark | Professional › Finance, accounting & tax | 83.2 | 83.2 | 0.0 |
Data: Artificial Analysis, Surge AI, Vals AI and 5 othersatlas.village.dev