Grok 4.3 (Medium): benchmark results
Provider: xAI. Released 2026-04-30. Access: API.
Unified ELO 1677 ± 1, rank #203 of 3081 rated models, from 46 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA IFBench | 83.33 | Accuracy (%) | 100 |
| IFBench | 83.33 | Score (%) | 100 |
| AA-Omniscience Hallucination Rate | 16.94 | Hallucination Rate (%) | 99.1 |
| AA-Omniscience Index - Health | 9.1 | Omniscience Index | 95.1 |
| AA-Omniscience Index - Business | 13.1 | Omniscience Index | 92.5 |
| AA-Omniscience Index - Law | 15.8 | Omniscience Index | 92 |
| AA-Omniscience Index - Science, Engineering & Mathematics | 14.3 | Omniscience Index | 91.8 |
| AA-Omniscience Index - Humanities & Social Sciences | 17.1 | Omniscience Index | 91.7 |
| AA Omniscience | 16.7 | Score | 91.1 |
| AA-Omniscience Index - Software Engineering (SWE) - TypeScript | 44.44 | Omniscience Index | 87.6 |
| AA-Omniscience Index - Software Engineering (SWE) - R | 22 | Omniscience Index | 87.3 |
| AA-Omniscience Index - Software Engineering (SWE) - Java | 7 | Omniscience Index | 87.1 |
Interactive version: theaggregate.ai/model?slug=grok-4-3-medium · How It Works · Data refreshed daily, snapshot 2026-09-21.