Grok 4 vs Kimi K3
Grok 4 (xAI) and Kimi K3 (Moonshot) compared on benchmarks, pricing, context window, and use-case rankings.
- Kimi K3 leads on overall intelligence (ECI 157 vs 147).
- Kimi K3 ranks higher for coding (99th vs 43th percentile).
| Attribute | Grok 4 | Kimi K3 |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | 147 | 157 |
| Coding | 43 | 99 |
| Math | 23 | 82 |
| Reasoning & Knowledge | 48 | 78 |
| Agentic & Tools | 15 | 84 |
| Specifications | ||
| Developer | xAI | Moonshot |
| Family | Grok | Kimi |
| Released | Jul 9, 2025 | Jul 16, 2026 |
| Parameters | 3T | 2.8T |
| Availability | API access | Open weights (non-commercial) |
| Context window | — | 1M |
| Price — $/M input | — | $2.80 |
| Price — $/M output | — | $14.00 |
| Inputs | — | text, image, video |
| Outputs | — | text |
| Benchmarks | ||
| AIME 2024/2025 | 84% | 97% |
| APEX | 15% | 39% |
| ARC-AGI | 67% | 95% |
| ARC-AGI-2 | 16% | 60% |
| FrontierMath | 20% | — |
| FrontierMath Tier 4 | 2% | — |
| GDPval (win/tie rate) | 24% | — |
| GPQA Diamond | 87% | 93% |
| Humanity's Last Exam | 27% | 47% |
| LiveCodeBench | 82% | — |
| METR task horizon | 1.8 h | — |
| MMLU-Pro | 87% | — |
| SciCode | 46% | 59% |
| SimpleBench | 61% | — |
| SimpleQA Verified | 48% | 43% |
| Terminal-Bench | 27% | — |
| WeirdML | 46% | 83% |
| τ²-bench | 75% | — |
| WebDev Arena | — | 1682 |
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 Kimi K3?
On Epoch AI's Capabilities Index, Kimi K3 scores higher (157) 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 Kimi K3?
Across coding benchmarks like SWE-bench Verified and Terminal-Bench, Kimi K3 ranks higher — 99th 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.