Grok 4.7 (Low): benchmark results
Provider: xAI. Released 2026-09-21. Access: API.
Aggregate Rating 1799 ± 12, rank #147 of 2257 rated models, from 109 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Omniscience | 29.62 | Score | 93.5 |
| AI for Education Pedagogy - Maths | 92.86 | Accuracy (%) | 93 |
| AI for Education Pedagogy - Science | 93.44 | Accuracy (%) | 92.4 |
| Wolfram LLM Benchmarking Project | 67.1 | Correct Functionality (%) | 90.6 |
| AI for Education Pedagogy - Primary | 93.9 | Accuracy (%) | 90.5 |
| ObviousBench | 99.31 | Answer pass³ (%) | 89.9 |
| AI for Education Pedagogy | 89.43 | Accuracy (%) | 88.7 |
| AA-Omniscience Accuracy | 49.7 | Accuracy (%) | 88.3 |
| AutomationBench-AA - Finance - Raw Objective Completion | 88.28 | Raw Objective Completion (%) | 87.1 |
| AI for Education SEND | 84.4 | Accuracy (%) | 86.7 |
| AA-Briefcase - Analytical Quality Elo | 1721.61 | Elo | 86.6 |
| AA-Omniscience Hallucination Rate | 39.93 | Hallucination Rate (%) | 86.6 |
Interactive version: theaggregate.ai/model?slug=grok-4-7-low · How It Works · Data refreshed daily, snapshot 2026-11-17.