Grok 4.6 vs Grok 4.7
Grok 4.6 (xAI) and Grok 4.7 (xAI) compared on benchmarks, pricing, context window, and use-case rankings.
- Grok 4.7 is cheaper on input tokens — $1.60 vs $2.00 per 1M.
- Grok 4.7 ranks higher for coding (92th vs 90th percentile).
| Attribute | Grok 4.6 | Grok 4.7 |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | 156 | — |
| Coding | 90 | 92 |
| Math | 91 | — |
| Reasoning & Knowledge | 73 | 86 |
| Agentic & Tools | 95 | — |
| Specifications | ||
| Developer | xAI | xAI |
| Family | Grok | Grok |
| Released | Aug 12, 2026 | Sep 21, 2026 |
| Parameters | — | 2.1B |
| Availability | API access | API access |
| Context window | 500K | 500K |
| Price — $/M input | $2.00 | $1.60 |
| Price — $/M output | $6.00 | $4.80 |
| Inputs | text, image, file | text, image, file |
| Outputs | text | text |
| Benchmarks | ||
| AIME 2024/2025 | 99% | — |
| APEX | 65% | — |
| ARC-AGI | 88% | — |
| ARC-AGI-2 | 67% | — |
| GPQA Diamond | 94% | — |
| Humanity's Last Exam | 43% | 43% |
| SciCode | 56% | 57% |
| SimpleBench | 76% | — |
| SimpleQA Verified | 49% | — |
| WebDev Arena | 1618 | — |
| WeirdML | 67% | — |
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
Which is cheaper, Grok 4.6 or Grok 4.7?
Grok 4.7 is cheaper on input tokens at $1.60 per million, versus $2.00 (representative OpenRouter pricing).
Which has a larger context window, Grok 4.6 or Grok 4.7?
Grok 4.6 supports up to 500K tokens, compared with 500K for the other.
Which is better for coding, Grok 4.6 or Grok 4.7?
Across coding benchmarks like SWE-bench Verified and Terminal-Bench, Grok 4.7 ranks higher — 92th vs 90th 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.