DeepSeek-V4-Pro-0813 vs Grok 4.6
DeepSeek-V4-Pro-0813 (DeepSeek) 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 155).
- DeepSeek-V4-Pro-0813 is cheaper on input tokens — $0.35 vs $2.00 per 1M.
- DeepSeek-V4-Pro-0813 has a larger context window (1M vs 500K tokens).
- Grok 4.6 ranks higher for coding (86th vs 71th percentile).
| Attribute | DeepSeek-V4-Pro-0813 | Grok 4.6 |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | 155 | 156 |
| Coding | 71 | 86 |
| Math | 82 | 87 |
| Reasoning & Knowledge | 65 | 69 |
| Agentic & Tools | 60 | 91 |
| Specifications | ||
| Developer | DeepSeek | xAI |
| Family | DeepSeek | Grok |
| Released | Aug 13, 2026 | Aug 12, 2026 |
| Parameters | 1.6T | — |
| Availability | Open weights (unrestricted) | API access |
| Context window | 1M | 500K |
| Price — $/M input | $0.35 | $2.00 |
| Price — $/M output | $4.20 | $6.00 |
| Inputs | text | text, image, file |
| Outputs | text | text |
| Benchmarks | ||
| AIME 2024/2025 | 99% | 99% |
| APEX | 47% | 65% |
| ARC-AGI | 91% | 88% |
| ARC-AGI-2 | 61% | 67% |
| GPQA Diamond | 92% | 94% |
| Humanity's Last Exam | 41% | 43% |
| SciCode | 51% | 56% |
| SimpleQA Verified | 53% | 49% |
| WebDev Arena | 1581 | 1618 |
| WeirdML | 66% | 67% |
| SimpleBench | — | 76% |
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 DeepSeek-V4-Pro-0813 better than Grok 4.6?
On Epoch AI's Capabilities Index, Grok 4.6 scores higher (156) than DeepSeek-V4-Pro-0813 (155). The right pick depends on your task — compare their coding, math, and reasoning scores in the table above.
Which is cheaper, DeepSeek-V4-Pro-0813 or Grok 4.6?
DeepSeek-V4-Pro-0813 is cheaper on input tokens at $0.35 per million, versus $2.00 (representative OpenRouter pricing).
Which has a larger context window, DeepSeek-V4-Pro-0813 or Grok 4.6?
DeepSeek-V4-Pro-0813 supports up to 1M tokens, compared with 500K for the other.
Which is better for coding, DeepSeek-V4-Pro-0813 or Grok 4.6?
Across coding benchmarks like SWE-bench Verified and Terminal-Bench, Grok 4.6 ranks higher — 86th vs 71th 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.