Grok 4.7 (High): benchmark results
Provider: xAI. Access: API.
Unified ELO 1752 ± 1, rank #26 of 3040 rated models, from 61 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AutomationBench-AA - Finance - Raw Objective Completion | 92.19 | Raw Objective Completion (%) | 99.4 |
| AA-Briefcase - DOCX - Rubric Pass Rate | 57.99 | Rubric Pass Rate (%) | 98.8 |
| AutomationBench-AA - Strict | 37.75 | Strict Task Success (%) | 98.5 |
| AA GDPval | 1693.72 | ELO | 98.3 |
| AA-Omniscience Index - Science, Engineering & Mathematics | 26.4 | Omniscience Index | 97.9 |
| AA-Briefcase - Analytical Quality Elo | 1967.4 | Elo | 97.7 |
| AutomationBench-AA - Support - Raw Objective Completion | 90.97 | Raw Objective Completion (%) | 97.6 |
| AA-Omniscience Index - Business | 25.8 | Omniscience Index | 97.5 |
| Artificial Analysis Intelligence Index | 46.33 | Intelligence Index | 97.5 |
| AA-Omniscience Index - Humanities & Social Sciences | 31.1 | Omniscience Index | 97.2 |
| AA Omniscience | 30.9 | Score | 96.8 |
| AA-Omniscience Index - Health | 14.8 | Omniscience Index | 96.6 |
Interactive version: theaggregate.ai/model?slug=grok-4-7-high · How It Works · Data refreshed daily, snapshot 2026-09-22.