Grok 4.6 vs Kimi K3
Grok 4.6 
Kimi K3 Verdict
- Kimi K3 leads on quality: 66.5 vs 63.8.
- Grok 4.6 (medium) is stronger in composite, knowledge, reasoning.
- Kimi K3 is stronger in coding, long context, agents & tools, human preference, maths, multimodal.
- Grok 4.6 (medium) is 2.0× cheaper ($3.00 vs $6.00 per 1M blended).
- Grok 4.6 (medium) streams 1.5× faster (55 vs 37 tokens per second).
| Metric | Grok 4.6 (medium) | Kimi K3 |
|---|---|---|
| BenchLeader Index | 63.8 | 66.5 |
| Coding score | 63.9 | 64.9 |
| Composite score | 83.2 | 74.1 |
| Knowledge score | 77.3 | 68.1 |
| Long context score | 67.1 | 71.1 |
| Reasoning score | 62.1 | – |
| Agents & tools score | – | 67.5 |
| Human preference score | – | 71.2 |
| Maths score | – | 78.1 |
| Multimodal score | – | 65.1 |
| Blended price $/M | $3.00 | $6.00 |
| Output speed | 55 tok/s | 37 tok/s |
| Time to first answer | 36.7 s | 57.7 s |
| Context window | 500k | 1.0M |
| SciCode | 54.6% | 58.7% |
| APEX-Agents | – | 39.3% |
| FrontierCode | – | 44.2% |
| ProofBench | – | 87.0% |
| Epoch Capabilities Index | – | 157.6 |
| LiveBench | – | 79.2% |
| LiveBench Reasoning | – | 90.7% |
| LiveBench Coding | – | 81.5% |
| LiveBench Agentic Coding | – | 62.2% |
| LiveBench Mathematics | – | 84.4% |
| LiveBench Data Analysis | – | 78.7% |
| LiveBench Language | – | 85.5% |
| AA Intelligence Index | 43.0 | 43.8 |
| AA-LCR | 81.0% | 88.7% |
| MMMU-Pro | – | 80.5% |
| AA-Omniscience | 28 | 19.7 |
| GPQA Diamond (AA) | 93.5% | 93.5% |
| Humanity's Last Exam (AA) | 42.1% | 46.9% |
| SciCode (AA) | 55.9% | 59.5% |
| LegalBench | – | 86.0% |
| CorpFin | – | 71.6% |
| TaxEval | – | 75.7% |
| Terminal-Bench 2.1 (Vals) | – | 80.9% |
| SWE-bench (Vals) | – | 93.4% |
| GPQA Diamond (Vals) | – | 92.9% |
| Vals Index | – | 57.8 |
| EQ-Bench 4 | – | 1339 |
| ARC-AGI-1 | 87.5% | – |
| ARC-AGI-2 | 61.3% | – |
Data as of 2026-09-09. Best configuration of each model; every score links to its source on the model pages.