# DeepSeek V4 Pro 0813 vs Kimi K2.6

> Side-by-side benchmark comparison for DeepSeek V4 Pro 0813 and Kimi K2.6 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/deepseek-v4-pro-0813-vs-kimi-2-6
- Last updated: September 14, 2026

- Shared sourced benchmarks: 18
- HTML indexing: indexable
- Ranking lane: BenchAlign v5

## Quick Verdict

Pick DeepSeek V4 Pro 0813 if you want the stronger benchmark profile. Kimi K2.6 only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- DeepSeek V4 Pro 0813 leads overall 66.39 to 65.46.
- The clearest category separation is in agentic, where the averages are 56.5 for DeepSeek V4 Pro 0813 and 46.6 for Kimi K2.6.
- The biggest single benchmark swing is SWE-bench (Vals) in Coding, with scores of 96.4% and 76.2%.
- DeepSeek V4 Pro 0813 is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- DeepSeek V4 Pro 0813 also has the larger context window at 1M.

## Model Snapshot

| Property | DeepSeek V4 Pro 0813 | Kimi K2.6 |
|----------|----------|----------|
| Creator | DeepSeek | Moonshot AI |
| Type | Proprietary | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 1M | 256K |
| Overall Score | 66.39 | 65.46 |
| Benchmarks Covered | 40 | 37 |
| Pricing (input/output) | $0.435 / $0.87 | $0.95 / $4.00 |

## Category Breakdown

### Agentic

- Winner: DeepSeek V4 Pro 0813
- DeepSeek V4 Pro 0813 public-lane score: 56.5 (Supported · #34/153)
- Kimi K2.6 public-lane score: 46.6 (Supported · #77/153)

| Benchmark | DeepSeek V4 Pro 0813 | Kimi K2.6 | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 67.9% | 66.7% | DeepSeek V4 Pro 0813 |
| Terminal-Bench 2.1 | 87.9% | Coming soon | Coming soon |
| BrowseComp | 83.4% | 83.2% | DeepSeek V4 Pro 0813 |
| HLE w/ tools | 60.0% | Coming soon | Coming soon |
| MCP Atlas | 73.6% | 55.9% | DeepSeek V4 Pro 0813 |
| Toolathlon | 51.8% | 50% | DeepSeek V4 Pro 0813 |
| CyberGym | 83.3% | Coming soon | Coming soon |
| Toolathlon-Verified | 74.1% | Coming soon | Coming soon |
| Agents' Last Exam | 25.7% | Coming soon | Coming soon |
| AutomationBench | 31.8% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 54.7% | 53.6% | DeepSeek V4 Pro 0813 |
| OSWorld-Verified | Coming soon | 73.1% | Coming soon |
| Claw-Eval | Coming soon | 62.3% | Coming soon |
| DeepSearchQA | Coming soon | 92.5% | Coming soon |
| WideResearch | Coming soon | 80.8% | Coming soon |
| Gert Labs | Coming soon | 56.82% | Coming soon |
| ResearchClawBench | Coming soon | 18.0% | Coming soon |
| OSWorld 2.0 | Coming soon | 4.6% | Coming soon |

### Coding

- Winner: DeepSeek V4 Pro 0813
- DeepSeek V4 Pro 0813 public-lane score: 51.9 (Supported · #49/152)
- Kimi K2.6 public-lane score: 50.8 (Supported · #53/152)

| Benchmark | DeepSeek V4 Pro 0813 | Kimi K2.6 | Winner |
|-----------|-----------|-----------|--------|
| LiveCodeBench Pass@1-COT | 93.5% | Coming soon | Coming soon |
| Codeforces | 3206.0 | Coming soon | Coming soon |
| SWE-bench Verified | 80.6% | 80.2% | DeepSeek V4 Pro 0813 |
| SWE-bench Pro | 55.4% | 58.6% | Kimi K2.6 |
| SWE Multilingual | 76.2% | 76.7% | Kimi K2.6 |
| Terminal-Bench 2.0 | 67.9% | 66.7% | DeepSeek V4 Pro 0813 |
| Vibe Code Bench | 49.93% | 37.89% | DeepSeek V4 Pro 0813 |
| Terminal-Bench 2.1 | 87.9% | Coming soon | Coming soon |
| NL2Repo | 61.5% | Coming soon | Coming soon |
| DeepSWE | 62.7% | Coming soon | Coming soon |
| DSBench-FullStack | 71.1% | Coming soon | Coming soon |
| DSBench-Hard | 67.2% | Coming soon | Coming soon |
| OpenHarmony Bench | 59.0% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 87.5% | 86.8% | DeepSeek V4 Pro 0813 |
| SWE-bench (Vals) | 96.4% | 76.2% | DeepSeek V4 Pro 0813 |
| LiveCodeBench v6 | Coming soon | 89.6% | Coming soon |
| SciCode | Coming soon | 52.2% | Coming soon |
| cursorBench31 | Coming soon | 47.6% | Coming soon |

### Multimodal & Grounded

- Winner: Coming soon
- DeepSeek V4 Pro 0813 public-lane score: Coming soon
- Kimi K2.6 public-lane score: 64 (#26/48)

| Benchmark | DeepSeek V4 Pro 0813 | Kimi K2.6 | Winner |
|-----------|-----------|-----------|--------|
| MMMU-Pro | Coming soon | 79.4% | Coming soon |
| MMMU-Pro w/ Python | Coming soon | 80.1% | Coming soon |
| CharXiv | Coming soon | 80.4% | Coming soon |
| MathVision | Coming soon | 87.4% | Coming soon |
| V* | Coming soon | 96.9% | Coming soon |

### Reasoning

- Winner: Coming soon
- DeepSeek V4 Pro 0813 public-lane score: 60.3 (#15/20)
- Kimi K2.6 public-lane score: Coming soon

| Benchmark | DeepSeek V4 Pro 0813 | Kimi K2.6 | Winner |
|-----------|-----------|-----------|--------|
| MRCR 1M | 83.5% | Coming soon | Coming soon |
| CorpusQA 1M | 62.0% | Coming soon | Coming soon |

### Knowledge

- Winner: Coming soon
- DeepSeek V4 Pro 0813 public-lane score: 59.8 (Estimated · #38/183)
- Kimi K2.6 public-lane score: 61.4 (Supported · #32/183)

| Benchmark | DeepSeek V4 Pro 0813 | Kimi K2.6 | Winner |
|-----------|-----------|-----------|--------|
| MMLU-Pro | 87.5% | Coming soon | Coming soon |
| SimpleQA | 57.9% | Coming soon | Coming soon |
| Chinese-SimpleQA | 84.4% | Coming soon | Coming soon |
| GPQA | 90.1% | 90.5% | Kimi K2.6 |
| GPQA-D | 90.1% | 90.5% | Kimi K2.6 |
| HLE | 42.7% | 34.7% | DeepSeek V4 Pro 0813 |
| GPQA Diamond (Vals) | 92.4% | 89.1% | DeepSeek V4 Pro 0813 |
| MMLU-Pro (Vals) | 87.0% | 87.6% | Kimi K2.6 |

### Mathematics

- Winner: Coming soon
- DeepSeek V4 Pro 0813 public-lane score: 80.4 (Unranked · 4 rankable rows)
- Kimi K2.6 public-lane score: 71.3 (#1/7)

| Benchmark | DeepSeek V4 Pro 0813 | Kimi K2.6 | Winner |
|-----------|-----------|-----------|--------|
| HMMT Feb 2026 | 95.2% | 92.7% | DeepSeek V4 Pro 0813 |
| IMOAnswerBench | 89.8% | Coming soon | Coming soon |
| Apex | 38.3% | Coming soon | Coming soon |
| Apex Shortlist | 90.2% | Coming soon | Coming soon |
| AIME26 | Coming soon | 96.4% | Coming soon |
| MMAnswerBench | Coming soon | 86.0% | Coming soon |
| FrontierMath v2 (Tiers 1-3) | Coming soon | 38.966% | Coming soon |
| FrontierMath v2 (Tier 4) | Coming soon | 14.580% | Coming soon |

## FAQ

### Which is better overall, DeepSeek V4 Pro 0813 or Kimi K2.6?

DeepSeek V4 Pro 0813 is ahead overall on BenchLM right now.

### Where is the biggest gap between DeepSeek V4 Pro 0813 and Kimi K2.6?

The widest category gap is in agentic, where the averages are 56.5 for DeepSeek V4 Pro 0813 and 46.6 for Kimi K2.6.

### How many benchmarks does DeepSeek V4 Pro 0813 cover on BenchLM?

DeepSeek V4 Pro 0813 currently has 40 sourced benchmark scores on BenchLM.

### How many benchmarks does Kimi K2.6 cover on BenchLM?

Kimi K2.6 currently has 37 sourced benchmark scores on BenchLM.

## Related Comparisons

- [DeepSeek V4 Pro 0813 vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-deepseek-v4-pro-0813)
- [Kimi K2.6 vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-kimi-2-6)
- [DeepSeek V4 Pro 0813 vs GPT-6 Astra](/compare/deepseek-v4-pro-0813-vs-gpt-6-astra)
- [Kimi K2.6 vs GPT-6 Astra](/compare/gpt-6-astra-vs-kimi-2-6)

## Explore More

- [DeepSeek V4 Pro 0813 profile](/models/deepseek-v4-pro-0813)
- [Kimi K2.6 profile](/models/kimi-2-6)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)