Grok 4.6 vs Kimi K2
Grok 4.6 (xAI) and Kimi K2 (Moonshot) compared on benchmarks, pricing, context window, and use-case rankings.
- Grok 4.6 leads on overall intelligence (ECI 156 vs 140).
- Kimi K2 is cheaper on input tokens — $0.57 vs $2.00 per 1M.
- Grok 4.6 has a larger context window (500K vs 131K tokens).
- Grok 4.6 ranks higher for coding (92th vs 8th percentile).
| Attribute | Grok 4.6 | Kimi K2 |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | 156 | 140 |
| Coding | 92 | 8 |
| Math | 92 | 5 |
| Reasoning & Knowledge | 74 | 14 |
| Agentic & Tools | 84 | 16 |
| Specifications | ||
| Developer | xAI | Moonshot |
| Family | Grok | Kimi |
| Released | Aug 12, 2026 | Sep 5, 2025 |
| Parameters | — | 1T |
| Availability | API access | Open weights (restricted use) |
| Context window | 500K | 131K |
| Price — $/M input | $2.00 | $0.57 |
| Price — $/M output | $6.00 | $2.30 |
| Inputs | text, image, file | text |
| Outputs | text | text |
| Benchmarks | ||
| AIME 2024/2025 | 99% | 57% |
| APEX | 41% | — |
| ARC-AGI | 88% | — |
| ARC-AGI-2 | 67% | — |
| GPQA Diamond | 94% | 77% |
| Humanity's Last Exam | 43% | 7% |
| SciCode | 56% | 35% |
| SimpleBench | 76% | 26% |
| SimpleQA Verified | 49% | — |
| WebDev Arena | 1629 | — |
| WeirdML | 67% | 39% |
| GSO (code optimization) | — | 5% |
| LiveCodeBench | — | 56% |
| MMLU-Pro | — | 82% |
| Terminal-Bench | — | 28% |
| τ²-bench | — | 61% |
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 4.6 better than Kimi K2?
On Epoch AI's Capabilities Index, Grok 4.6 scores higher (156) than Kimi K2 (140). The right pick depends on your task — compare their coding, math, and reasoning scores in the table above.
Which is cheaper, Grok 4.6 or Kimi K2?
Kimi K2 is cheaper on input tokens at $0.57 per million, versus $2.00 (representative OpenRouter pricing).
Which has a larger context window, Grok 4.6 or Kimi K2?
Grok 4.6 supports up to 500K tokens, compared with 131K for the other.
Which is better for coding, Grok 4.6 or Kimi K2?
Across coding benchmarks like SWE-bench Verified and Terminal-Bench, Grok 4.6 ranks higher — 92th vs 8th 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.