Grok 4.7 vs Hy4
Hy4 leads by 1.3 capability points (≈95% interval −1.2 to +3.8): statistically tied · P(higher) ≈ 84%
Grok 4.7 wins 10 of 16 shared benchmarks (5 lost, 1 tied)
Capability vs. relative cost
Grok 4.7Hy4Closed weightsOpen weights
Hy4 has no setting with a relative cost yet.
Benchmark wins10 – 5 · 16 shared, 1 tied
Comparing matching setups only (162 benchmarks excluded) · suites counted once
Area← Grok 4.7Hy4 →
Data: Surge AI, Mercor, Collinear AI and 3 othersatlas.village.dev
Margins
Each benchmark scaled 0–100% (its declared range, else the field’s range); Δ is Hy4 minus Grok 4.7.
| Chartography (November 2026 rescoring) | Perception & media › Documents & charts | 74.6 | 49.2 | −25.4 |
| DAYJOB: Healthcare (October 2026 rescoring) | Health & medicine | 27.6 | 7.2 | −20.4 |
| HANDBOOK.md Agents v1.1 | Tool & computer use › Customer service & operations | 44.0 | 23.7 | −20.3 |
| DAYJOB: Finance (October 2026 rescoring) | Professional › Finance, accounting & tax | 26.5 | 9.2 | −17.3 |
| τ³-Banking (Mercor run, bm25_grep retrieval) | Tool & computer use › Customer service & operations | 32.6 | 48.1 | +15.5 |
| CWE-bench v2 Pass@1 | Software › Cybersecurity | 54.7 | 64.1 | +9.4 |
| LLM Debate Benchmark | Language & writing › Language & wordplay | 1601 | 1647 | +6.5 |
| RiemannBench (November 2026 rescoring) | Math | 57.6 | 51.2 | −6.4 |
| ComplexConstraints (November 2026 rescoring) | Language & writing › Instruction following | 60.8 | 66.8 | +6.0 |
| Harvey LAB (Mercor run, undisclosed ~213-task cohort) | Professional › Legal | 19.5 | 13.6 | −5.9 |
| DAXBench v2 | Software › Data & ML | 92.6 | 87.2 | −5.3 |
| GDP.pdf (November 2026 rescoring) | Professional › General knowledge work | 48.8 | 43.6 | −5.2 |
| APEX-Agents 1.1 | Professional › General knowledge work | 80.4 | 85.1 | +4.7 |
| GDP.xlsx | Professional › General knowledge work | 22.3 | 17.7 | −4.6 |
| Design Arena Overall Code Categories | Software › Frontend & design | 1270 | 1260 | −1.7 |
| EnterpriseBench: CoreCraft | Tool & computer use › Customer service & operations | 68.2 | 68.2 | 0.0 |
Data: Surge AI, Mercor, Collinear AI and 3 othersatlas.village.dev