Grok 4.6 (xHigh): benchmark results
Provider: xAI. Released 2026-08-12. Access: API.
Aggregate Rating 1853 ± 10, rank #62 of 2168 rated models, from 146 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| ExplorationBench - AlienLogic | 83.8 | Held-out accuracy after exploration (%; Best@3: the highest | 100 |
| SWEeper-Bench - Pass | 59 | Pass rate (%; 200 interactive software bug-discovery tasks; | 100 |
| SWEeper-Bench - Target | 59 | Target rate (%; 200 interactive software bug-discovery tasks | 100 |
| SciUniverse - Identify unsuitable MRM peaks | 4.4 | Pass@1 (%) | 100 |
| AutomationBench-AA - Finance - Raw Objective Completion | 92.16 | Raw Objective Completion (%) | 97.8 |
| AA GPQA Diamond | 93.54 | Accuracy (%) | 97.4 |
| AutomationBench-AA - Sales - Raw Objective Completion | 87.62 | Raw Objective Completion (%) | 97.3 |
| PetriBench - MinimumTokenSteps (Hard) | 74 | Exact-Match Accuracy (%) | 97.1 |
| AA-Omniscience Hallucination Rate | 24.01 | Hallucination Rate (%) | 96.5 |
| AutomationBench-AA | 67 | Guardrail-Adjusted Objective Completion (%) | 96 |
| BVB | 67.17 | Overall (%) | 96 |
| AA-Briefcase - Presentation Elo | 1532.82 | Elo | 95.3 |
Interactive version: theaggregate.ai/model?slug=grok-4-6-xhigh · How It Works · Data refreshed daily, snapshot 2026-10-20.