Grok 4.7 vs Muse Ember
Muse Ember leads by 1.6 capability points (≈95% interval −0.7 to +3.9): statistically tied · P(higher) ≈ 91%
Grok 4.7 wins 36 of 61 shared benchmarks (24 lost, 1 tied)
Capability vs. relative cost
Grok 4.7Muse EmberClosed weightsOpen weights
Benchmark wins36 – 24 · 61 shared, 1 tied
Comparing matching setups only (3 benchmarks excluded) · suites counted once
Area← Grok 4.7Muse Ember →
Data: Artificial Analysis, Vals AI, Surge AI and 10 othersatlas.village.dev
Margins
Each benchmark scaled 0–100% (its declared range, else the field’s range); Δ is Muse Ember minus Grok 4.7.
| DAXBench v2 | Software › Data & ML | 92.6 | 62.8 | −29.8 |
| τ³-Banking (Mercor run, bm25_grep retrieval) | Tool & computer use › Customer service & operations | 32.6 | 53.3 | +20.7 |
| HANDBOOK.md Agents v1.1 | Tool & computer use › Customer service & operations | 44.0 | 29.8 | −14.2 |
| Ramp SWE-Bench v2 | Software › Software engineering | 64.4 | 51.8 | −12.6 |
| AA-Omniscience v1.1 Index | Knowledge & reasoning › General knowledge | 31.2 | 7.7 | −11.7 |
| Terminal-Bench 4.0 | Software › Software engineering | 28.8 | 39.4 | +10.6 |
| CritPt v2 (agentic, avg@5) | Science › Physical sciences | 51.4 | 62.0 | +10.6 |
| DAYJOB: Healthcare (October 2026 rescoring) | Health & medicine | 27.6 | 17.2 | −10.4 |
| Terminal-Bench 4.0 (Artificial Analysis) | Software › Software engineering | 25.8 | 35.4 | +9.6 |
| Artificial Analysis Legal Index | Professional › Legal | 47.2 | 38.5 | −8.7 |
| BuseyBench SVG | Perception & media › Generation | 4.6 | 5.4 | +8.3 |
| Artificial Analysis Finance & Accounting Index | Professional › Finance, accounting & tax | 51.7 | 44.6 | −7.1 |
| GDP.xlsx | Professional › General knowledge work | 22.3 | 15.4 | −6.9 |
| FrontierCode 2.0 (Artificial Analysis) | Software › Software engineering | 28.7 | 22.0 | −6.7 |
| HLAB-Vals-1.1 | Professional › Legal | 18.3 | 25.0 | +6.7 |
| Terminal-Bench-Science 0.1 | Science › Multidisciplinary | 11.4 | 17.6 | +6.2 |
| Artificial Analysis Strategy & Ops Index | Professional › General knowledge work | 54.8 | 48.7 | −6.1 |
| SWE Atlas v1.1 - Overall | Software › Software engineering | 62.1 | 56.0 | −6.1 |
| EnterpriseBench: CoreCraft | Tool & computer use › Customer service & operations | 68.2 | 62.1 | −6.1 |
| TaxCalcBench TY25 | Professional › Finance, accounting & tax | 8.0 | 2.0 | −6.0 |
| AA-Briefcase v1.1 Elo | Professional › General knowledge work | 1634 | 1526 | −5.9 |
| FORTRESS Average Risk Score (ARS) | Safety & alignment | 6.3 | 11.9 | −5.6 |
| Artificial Analysis Healthcare & Medical Index | Health & medicine | 46.6 | 41.3 | −5.3 |
| APEX-1 (Mercor, mean score) | Professional › General knowledge work | 65.4 | 70.4 | +5.0 |
| Artificial Analysis Economics Index | Composite indexes | 45.7 | 41.0 | −4.7 |
| Code Migration v1.1 (Vals Index v2.2 subset) | Software › Software engineering | 51.8 | 47.1 | −4.7 |
| APEX-Agents 1.1 | Professional › General knowledge work | 80.4 | 75.7 | −4.7 |
| Chartography (November 2026 rescoring) | Perception & media › Documents & charts | 74.6 | 79.3 | +4.7 |
| LMArena Agent Arena Steering Burden | Tool & computer use › General agents | -4.3 | 4.8 | +4.5 |
| GBENCH One-shot Coding GScore | Games | 60.5 | 56.4 | −4.1 |
| LMArena Code Arena WebDev | Software › Frontend & design | 1639 | 1608 | −4.1 |
| RiemannBench (November 2026 rescoring) | Math | 57.6 | 53.6 | −4.0 |
| Finance Agent v2.1 | Professional › Finance, accounting & tax | 60.6 | 63.8 | +3.2 |
| Harvey LAB (Mercor run, undisclosed ~213-task cohort) | Professional › Legal | 19.5 | 22.7 | +3.2 |
| Vals Legal Index | Professional › Legal | 72.7 | 75.7 | +3.0 |
| Medical Long Context Reasoning (MLCR-AA, October 2026 methodology) | Health & medicine | 21.1 | 18.3 | −2.8 |
| LMArena Agent Arena Confirmed Success | Tool & computer use › General agents | 3.5 | -2.0 | −2.8 |
| AutomationBench-AA 1.0.6 | Tool & computer use › Customer service & operations | 65.6 | 68.1 | +2.5 |
| Vibe Code Bench v1.1 | Software › Frontend & design | 86.2 | 83.7 | −2.5 |
| LMArena Agent Arena Praise vs Complaint | Tool & computer use › General agents | 2.1 | -2.7 | −2.4 |
| DeepFinance | Professional › Finance, accounting & tax | 34.1 | 36.5 | +2.4 |
| Tax Agent Bench | Professional › Finance, accounting & tax | 69.0 | 71.4 | +2.4 |
| DAYJOB: Finance (October 2026 rescoring) | Professional › Finance, accounting & tax | 26.5 | 24.2 | −2.3 |
| Artificial Analysis Progress Index v1 | Composite indexes | 323 | 329 | +2.1 |
| Vals Finance Index | Professional › Finance, accounting & tax | 58.8 | 60.9 | +2.1 |
| ComplexConstraints (November 2026 rescoring) | Language & writing › Instruction following | 60.8 | 58.8 | −2.0 |
| Artificial Analysis Coding Agent Index v2.1 | Software › Software engineering | 41.6 | 39.7 | −2.0 |
| Legal Research Bench | Professional › Legal | 47.1 | 49.0 | +1.9 |
| Vals Index v2.2 | Composite indexes | 58.6 | 60.5 | +1.9 |
| Humanity's Last Exam Diamond | Knowledge & reasoning › General knowledge | 23.6 | 25.1 | +1.5 |
| LMArena Agent Arena Net Improvement (Steering Burden) | Tool & computer use › General agents | 1.5 | 1.0 | −1.0 |
| LMArena Agent Arena Bash Reliability | Tool & computer use › General agents | 8.2 | 6.6 | −0.8 |
| Excel Modeling Benchmark v1.1 | Professional › Finance, accounting & tax | 71.5 | 72.2 | +0.7 |
| Artificial Analysis Coding Agent Index v2.0 | Software › Software engineering | 46.6 | 45.9 | −0.7 |
| Artificial Analysis Intelligence Index v5.0.1 | Composite indexes | 35.5 | 36.0 | +0.5 |
| APEX-SWE | Software › Software engineering | 53.4 | 52.9 | −0.5 |
| GDP.pdf (November 2026 rescoring) | Professional › General knowledge work | 48.8 | 49.2 | +0.4 |
| GDP.pdf (Artificial Analysis, All-pass) | Professional › General knowledge work | 23.2 | 22.8 | −0.4 |
| LMArena Agent Arena Tool Hallucination | Tool & computer use › Tool calling | 1.2 | 0.9 | −0.1 |
| Artificial Analysis Engineering Index | Science › Engineering | 41.8 | 41.8 | 0.0 |
| FrontierCUA v1 pass@1 | Tool & computer use › Computer & browser use | 7.5 | 7.5 | 0.0 |
Data: Artificial Analysis, Vals AI, Surge AI and 10 othersatlas.village.dev