Grok 4.5 (High) — benchmark results
Grok 4.5 evaluated at the high reasoning-effort setting. Provider: xAI. Released 2026-07-08. Access: API.
Unified ELO 1931 ± 21, rank #47 of 1776 rated models, from 51 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Omniscience | 26.38 | Score | 99.3 |
| AA GPQA Diamond | 93.13 | Accuracy (%) | 99 |
| Artificial Analysis Intelligence Index | 53.83 | Intelligence Index | 98.5 |
| AA Omniscience - Software Engineering (SWE) - R | 70 | Accuracy (%) | 98.4 |
| AA Omniscience - Health | 48.5 | Accuracy (%) | 98.2 |
| AA Omniscience - Science, Engineering & Mathematics | 51.8 | Accuracy (%) | 98.2 |
| Tau3 Banking | 32.58 | Success Rate (%) | 98.2 |
| AA Humanity's Last Exam | 40.27 | Accuracy (%) | 97.4 |
| AA SciCode | 54.05 | Accuracy (%) | 97.2 |
| AA-Omniscience Accuracy | 52.05 | Accuracy (%) | 97.1 |
| AA Omniscience - Humanities & Social Sciences | 50.2 | Accuracy (%) | 96.5 |
| AA Omniscience - Law | 50.1 | Accuracy (%) | 96.4 |
Interactive version: theaggregate.ai/model?slug=grok-4-5-high · How the rankings work · Data refreshed daily, snapshot 2026-07-22.