Grok 4.3 (Low): benchmark results
Provider: xAI. Released 2026-04-30. Access: API.
Unified ELO 1645 ± 1, rank #261 of 1761 rated models, from 18 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA IFBench | 80.95 | Accuracy (%) | 98.7 |
| CritPt | 60 | Accuracy (self-reported) | 91.9 |
| AA Omniscience | 13.93 | Score | 89.1 |
| AA TAU-2 Bench | 88.89 | Accuracy (%) | 83.3 |
| Artificial Analysis Intelligence Index | 28.53 | Intelligence Index | 78.8 |
| AA GPQA Diamond | 84.34 | Accuracy (%) | 75.9 |
| AA Long Context Reasoning | 74 | Accuracy (%) | 75.6 |
| AA Omniscience - Software Engineering (SWE) | 39.3 | Accuracy (%) | 71 |
| AA Humanity's Last Exam | 18.35 | Accuracy (%) | 69.7 |
| AA Omniscience - Science, Engineering & Mathematics | 34.9 | Accuracy (%) | 69.3 |
| AA Omniscience - Business | 22.2 | Accuracy (%) | 68.9 |
| AA Terminal-Bench Hard | 26.52 | Accuracy (%) | 68.1 |
Interactive version: theaggregate.ai/model?slug=grok-4-3-low · How It Works · Data refreshed daily, snapshot 2026-09-05.