Grok 4 vs Grok 4.6
Grok 4 (xAI) and Grok 4.6 (xAI) compared on benchmarks, pricing, context window, and use-case rankings.
- Grok 4.6 leads on overall intelligence (ECI 156 vs 147).
- Grok 4.6 ranks higher for coding (91th vs 43th percentile).
| Attribute | Grok 4 | Grok 4.6 |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | 147 | 156 |
| Coding | 43 | 91 |
| Math | 23 | 93 |
| Reasoning & Knowledge | 47 | 76 |
| Agentic & Tools | 15 | 89 |
| Specifications | ||
| Developer | xAI | xAI |
| Family | Grok | Grok |
| Released | Jul 9, 2025 | Aug 12, 2026 |
| Parameters | 3T | — |
| Availability | API access | API access |
| Context window | — | 500K |
| Price — $/M input | — | $2.00 |
| Price — $/M output | — | $6.00 |
| Inputs | — | text, image, file |
| Outputs | — | text |
| Benchmarks | ||
| AIME 2024/2025 | 84% | 99% |
| APEX | 15% | 41% |
| ARC-AGI | 67% | 88% |
| ARC-AGI-2 | 16% | 67% |
| FrontierMath | 20% | — |
| FrontierMath Tier 4 | 2% | — |
| GDPval (win/tie rate) | 24% | — |
| GPQA Diamond | 87% | 94% |
| Humanity's Last Exam | 27% | 43% |
| LiveCodeBench | 82% | — |
| METR task horizon | 1.8 h | — |
| MMLU-Pro | 87% | — |
| SciCode | 46% | 54% |
| SimpleBench | 61% | — |
| SimpleQA Verified | 48% | 54% |
| Terminal-Bench | 27% | — |
| WeirdML | 46% | 67% |
| τ²-bench | 75% | — |
| WebDev Arena | — | 1631 |
Use-case scores are 0–100 percentile composites across each area’s benchmarks, ranked against every model from the past year. Highlighted cells lead each row. Open a model for the full picture.
Frequently asked questions
Is Grok 4 better than Grok 4.6?
On Epoch AI's Capabilities Index, Grok 4.6 scores higher (156) than Grok 4 (147). The right pick depends on your task — compare their coding, math, and reasoning scores in the table above.
Which is better for coding, Grok 4 or Grok 4.6?
Across coding benchmarks like SWE-bench Verified and Terminal-Bench, Grok 4.6 ranks higher — 91th vs 43th percentile among the models tracked on Model Beat.
Want a different match-up? Open the compare tool to add or swap models.
More comparisons
Benchmarks & model data from Epoch AI (CC BY); pricing & specs from OpenRouter. ECI = Epoch Capabilities Index.