Deepseek v4 Pro vs Kimi K2.6
Deepseek v4 Pro 
Kimi K2.6 Verdict
- Deepseek v4 Pro (high) leads on quality: 60.4 vs 59.4.
- Deepseek v4 Pro (high) is stronger in human preference, maths.
- Kimi K2.6 is stronger in coding, reasoning, agents & tools, composite, instruction following, knowledge, long context, multimodal.
| Metric | Deepseek v4 Pro (high) | Kimi K2.6 |
|---|---|---|
| BenchLeader Index | 60.4 | 59.4 |
| Coding score | 59.3 | 60.3 |
| Human preference score | 66.0 | 60.7 |
| Maths score | 66.2 | 53.8 |
| Reasoning score | 65.9 | 66.0 |
| Agents & tools score | – | 44.1 |
| Composite score | – | 62.6 |
| Instruction following score | – | 70.6 |
| Knowledge score | – | 57.8 |
| Long context score | – | 64.7 |
| Multimodal score | – | 63.0 |
| Blended price $/M | – | $1.71 |
| Output speed | – | 36 tok/s |
| Time to first answer | – | 126.5 s |
| Context window | – | 262k |
| GPQA Diamond | 90.9% | 90.8% |
| FrontierMath Tiers 1–3 | – | 57.2% |
| FrontierMath Tier 4 | – | 25.6% |
| OTIS Mock AIME | 95.6% | 96.1% |
| SWE-bench Verified (Epoch) | – | 76.7% |
| SimpleQA Verified | – | 34.9% |
| OSWorld-Verified 2.0 | – | 4.6% |
| SciCode | 46.4% | 53.5% |
| WeirdML | 46.5% | 55.9% |
| APEX-Agents | – | 18.9% |
| ProofBench | – | 16.0% |
| Epoch Capabilities Index | – | 151.0 |
| LMArena Text | 1462 | 1461 |
| LMArena Hard Prompts | 1482 | 1485 |
| LMArena Coding | 1505 | 1514 |
| LMArena WebDev | 1581 | 1509 |
| LMArena Vision | – | 1281 |
| AA Intelligence Index | – | 31.3 |
| IFBench | – | 76.0% |
| AA-LCR | – | 81.0% |
| MMMU-Pro | – | 79.4% |
| AA-Omniscience | – | 5.3 |
| Terminal-Bench Hard | – | 43.9% |
| GPQA Diamond (AA) | – | 91.1% |
| Humanity's Last Exam (AA) | – | 37.5% |
| SciCode (AA) | – | 51.5% |
| τ²-Bench Telecom (AA) | – | 95.9% |
| LiveCodeBench | – | 86.8% |
| MMLU-Pro | – | 87.6% |
| LegalBench | – | 84.7% |
| CorpFin | – | 66.7% |
| TaxEval | – | 74.7% |
| Terminal-Bench 2.1 (Vals) | – | 53.6% |
| SWE-bench (Vals) | – | 76.2% |
| GPQA Diamond (Vals) | – | 89.1% |
| Vals Index | – | 43.5 |
| HiL-Bench | – | 18.7% |
| EQ-Bench 4 | – | 1202 |
Data as of 2026-09-13. Best configuration of each model; every score links to its source on the model pages.
Deepseek v4 Pro vs Kimi K2.6: questions
- Is Deepseek v4 Pro better than Kimi K2.6?
- Deepseek v4 Pro (high) leads on quality: 60.4 vs 59.4. The BenchLeader Index combines every independent quality benchmark; Deepseek v4 Pro (high) is ahead overall as of 2026-09-13, but check the category scores for your use.
- Is Deepseek v4 Pro better than Kimi K2.6 for coding?
- Kimi K2.6 scores higher in coding (60 vs 59 on the category index, where 50 is average).