Grok 4.7 (xHigh): benchmark results
Provider: xAI. Released 2026-09-21. Access: API.
Aggregate Rating 1844 ± 8, rank #84 of 2171 rated models, from 289 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Terminal-Bench 4.0 (Grok Build) | 37.58 | Resolution Rate (%) | 100 |
| AutomationBench-AA - Finance - Raw Objective Completion | 93.49 | Raw Objective Completion (%) | 98.4 |
| AA GDPval | 1718.42 | ELO | 96.1 |
| AA-Briefcase - Analytical Quality Elo | 1931.87 | Elo | 96 |
| AA-Briefcase - PDF - Rubric Pass Rate | 62.93 | Rubric Pass Rate (%) | 95 |
| AutomationBench-AA - Strict | 37.75 | Strict Task Success (%) | 94.9 |
| Chatbot Arena (Text - French) | 1509 | Arena Score | 94.9 |
| AA-Briefcase - DOCX - Rubric Pass Rate | 57.4 | Rubric Pass Rate (%) | 93.6 |
| Vals AI MedScribe | 89.38 | Accuracy (%) | 93.6 |
| AA-Omniscience Hallucination Rate | 20.01 | Hallucination Rate (%) | 93.4 |
| Harvey LAB-AA | 9.44 | Hallucination-Gated All-Pass Rate (%) | 92.6 |
| Harvey LAB-AA - Litigation & Dispute Resolution | 94.36 | Criterion Pass Rate (%) | 92.6 |
Interactive version: theaggregate.ai/model?slug=grok-4-7-xhigh · How It Works · Data refreshed daily, snapshot 2026-11-06.