Gemini 4 Neon vs Muse Wonder
TryTop 2 now
Gemini 4 Neon leads by 5.5 capability points (≈95% interval +2.8 to +8.3): a clear lead over Muse Wonder · P(higher) ≈ 100%
Wins 67 of 70 shared benchmarks (3 lost)
Capability vs. relative cost
Gemini 4 NeonMuse WonderClosed weightsOpen weights
Benchmark wins67 – 3 · 70 shared
Comparing matching setups only (2 benchmarks excluded) · suites counted once
Area← Gemini 4 NeonMuse 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 Gemini 4 Neon.
| Vending-Bench 2 | Business simulations | 16843 | 9432 | −43.9 |
| Terminal-Bench-Science 0.1 | Science › Multidisciplinary | 65.7 | 21.9 | −43.8 |
| Terminal-Bench Science 0.1 (Vals) | Science › Multidisciplinary | 62.9 | 22.9 | −40.0 |
| Furniture Assembly Benchmark | Perception & media › Spatial & visual reasoning | 89.2 | 54.2 | −35.0 |
| LMArena Agent Arena Net Improvement (Steering Burden) | Tool & computer use › General agents | 18.4 | 0.6 | −34.8 |
| Mystery Game Puzzles | Games | 85.0 | 51.0 | −34.0 |
| Humanity's Last Exam Diamond | Knowledge & reasoning › General knowledge | 71.3 | 39.0 | −32.3 |
| Humanity's Sixth Sense | Perception & media › Spatial & visual reasoning | 75.9 | 43.7 | −32.2 |
| Bug Hunt Bench | Software › Software engineering | 60.0 | 30.2 | −29.8 |
| FrontierMath Tier 4 (v2) - Private | Math | 97.6 | 70.7 | −26.8 |
| RiemannBench (November 2026 rescoring) | Math | 84.0 | 59.2 | −24.8 |
| SWE-Marathon v1.2 | Software › Software engineering | 62.5 | 38.1 | −24.4 |
| LMArena Agent Arena Praise vs Complaint | Tool & computer use › General agents | 44.5 | -3.0 | −23.7 |
| Vals Science Index | Science › Multidisciplinary | 62.6 | 39.1 | −23.5 |
| Terminal-Bench 4.0 (Artificial Analysis) | Software › Software engineering | 61.6 | 38.4 | −23.2 |
| HANDBOOK.md Agents v1.1 | Tool & computer use › Customer service & operations | 52.3 | 29.5 | −22.8 |
| sudo L7 (October 2026 rescoring) | Software › Software engineering | 38.3 | 16.1 | −22.2 |
| GDP.xlsx | Professional › General knowledge work | 43.1 | 21.8 | −21.3 |
| DAYJOB: Accounting | Professional › Finance, accounting & tax | 49.6 | 30.8 | −18.8 |
| Artificial Analysis Intelligence Index v5.0.1 | Composite indexes | 61.4 | 43.6 | −17.8 |
| MysteryMechanism | Math | 45.0 | 27.5 | −17.6 |
| Artificial Analysis Engineering Index | Science › Engineering | 66.8 | 49.6 | −17.3 |
| Artificial Analysis Legal Index | Professional › Legal | 63.8 | 46.9 | −16.9 |
| LiveBench 2.0 (2026-11-06 release) | Composite indexes | 87.4 | 70.7 | −16.7 |
| FrontierCode 2.0 (Artificial Analysis) | Software › Software engineering | 43.3 | 26.6 | −16.7 |
| DAYJOB: Healthcare (October 2026 rescoring) | Health & medicine | 47.2 | 31.2 | −16.0 |
| EnterpriseBench: CoreCraft | Tool & computer use › Customer service & operations | 77.4 | 61.5 | −15.9 |
| LMArena Code Arena WebDev | Software › Frontend & design | 1764 | 1648 | −15.4 |
| AA-Omniscience v1.1 Index | Knowledge & reasoning › General knowledge | 54.8 | 25.1 | −14.8 |
| Artificial Analysis Coding Agent Index v2.1 | Software › Software engineering | 58.6 | 44.5 | −14.2 |
| Artificial Analysis Finance & Accounting Index | Professional › Finance, accounting & tax | 65.1 | 51.1 | −13.9 |
| BioMysteryBench (Vals Terminus 2) | Science › Life sciences | 80.0 | 67.0 | −13.0 |
| Artificial Analysis Economics Index | Composite indexes | 61.9 | 49.5 | −12.4 |
| Terminal-Bench 4.0 | Software › Software engineering | 61.6 | 49.5 | −12.1 |
| APEX-Agents 1.1 | Professional › General knowledge work | 88.9 | 77.0 | −11.9 |
| DAYJOB: Finance (October 2026 rescoring) | Professional › Finance, accounting & tax | 50.5 | 38.8 | −11.7 |
| Artificial Analysis Healthcare & Medical Index | Health & medicine | 60.1 | 48.7 | −11.4 |
| AutomationBench-AA 1.0.6 | Tool & computer use › Customer service & operations | 79.3 | 68.1 | −11.2 |
| Vibe Code Bench v1.1 | Software › Frontend & design | 93.7 | 83.1 | −10.6 |
| LMArena Agent Arena Steering Burden | Tool & computer use › General agents | 21.2 | 1.5 | −9.8 |
| Medical Long Context Reasoning (MLCR-AA, October 2026 methodology) | Health & medicine | 31.7 | 22.2 | −9.4 |
| Artificial Analysis Strategy & Ops Index | Professional › General knowledge work | 63.8 | 54.5 | −9.3 |
| FrontierMath Tiers 1-3 (v2) - Private | Math | 91.2 | 82.1 | −9.1 |
| MKA (Artificial Analysis) | Professional › General knowledge work | 56.5 | 47.5 | −9.0 |
| Tax Agent Bench | Professional › Finance, accounting & tax | 79.8 | 71.2 | −8.6 |
| LMArena Agent Arena Confirmed Success | Tool & computer use › General agents | 19.2 | 2.5 | −8.4 |
| τ³-Banking (Mercor run, bm25_grep retrieval) | Tool & computer use › Customer service & operations | 59.5 | 51.9 | −7.6 |
| Agents' Last Exam v1.1 Score | Professional › General knowledge work | 75.8 | 68.4 | −7.4 |
| Vals Finance Index | Professional › Finance, accounting & tax | 68.3 | 61.2 | −7.1 |
| DAYJOB: Tax | Professional › Finance, accounting & tax | 12.8 | 6.0 | −6.8 |
| Vals Index v2.2 | Composite indexes | 70.9 | 64.9 | −6.0 |
| Code Migration v1.1 (Vals Index v2.2 subset) | Software › Software engineering | 75.8 | 69.8 | −6.0 |
| Legal Research Bench | Professional › Legal | 56.3 | 50.5 | −5.8 |
| CritPt v2 (agentic, avg@5) | Science › Physical sciences | 76.6 | 70.9 | −5.7 |
| DAYJOB: Law (November 2026 release) | Professional › Legal | 26.2 | 20.6 | −5.6 |
| ComplexConstraints (November 2026 rescoring) | Language & writing › Instruction following | 72.9 | 67.9 | −5.0 |
| LMArena Agent Arena Bash Reliability | Tool & computer use › General agents | -6.0 | 3.4 | +4.7 |
| CWE-bench v2 Pass@1 | Software › Cybersecurity | 70.7 | 66.1 | −4.6 |
| HLAB-Vals-1.1 | Professional › Legal | 19.6 | 23.8 | +4.2 |
| Excel Modeling Benchmark v1.1 | Professional › Finance, accounting & tax | 76.5 | 72.5 | −4.0 |
| APEX-Accounting 1.1 | Professional › Finance, accounting & tax | 70.8 | 67.1 | −3.7 |
| Harvey LAB (Mercor run, undisclosed ~213-task cohort) | Professional › Legal | 26.6 | 23.0 | −3.6 |
| Vals Legal Index | Professional › Legal | 78.4 | 75.3 | −3.1 |
| Finance Agent v2.1 | Professional › Finance, accounting & tax | 68.6 | 65.5 | −3.0 |
| GDP.pdf (Artificial Analysis, All-pass) | Professional › General knowledge work | 33.4 | 30.6 | −2.8 |
| GDP.pdf (November 2026 rescoring) | Professional › General knowledge work | 53.4 | 54.8 | +1.4 |
| LMArena Text Arena Elo | Language & writing › General assistance | 1518 | 1511 | −1.4 |
| AA-Briefcase v1.1 Elo | Professional › General knowledge work | 1632 | 1610 | −1.2 |
| LMArena Agent Arena Tool Hallucination | Tool & computer use › Tool calling | 1.0 | -0.2 | −0.6 |
| OTIS Mock AIME 2024-2025 | Math | 100.0 | 99.4 | −0.6 |
Data: Artificial Analysis, Vals AI, Surge AI and 11 othersatlas.village.dev