# DeepSeek V4 Pro 0813 vs Kimi K3

> Side-by-side benchmark comparison for DeepSeek V4 Pro 0813 and Kimi K3 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/deepseek-v4-pro-0813-vs-kimi-k3
- Last updated: September 4, 2026

- Shared sourced benchmarks: 14
- HTML indexing: indexable
- Ranking lane: BenchAlign v5

## Quick Verdict

Pick Kimi K3 if you want the stronger benchmark profile. DeepSeek V4 Pro 0813 only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- Kimi K3 leads overall 74.87 to 66.35.
- The clearest category separation is in reasoning, where the averages are 58.7 for DeepSeek V4 Pro 0813 and 78.5 for Kimi K3.
- The biggest single benchmark swing is Terminal-Bench 2.1 (Vals) in Agentic, with scores of 54.7% and 80.9%.
- DeepSeek V4 Pro 0813 is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- Kimi K3 also has the larger context window at 1.05M.

## Model Snapshot

| Property | DeepSeek V4 Pro 0813 | Kimi K3 |
|----------|----------|----------|
| Creator | DeepSeek | Moonshot AI |
| Type | Proprietary | Pending |
| Reasoning | Reasoning | Reasoning |
| Context | 1M | 1.05M |
| Overall Score | 66.35 | 74.87 |
| Benchmarks Covered | 39 | 43 |
| Pricing (input/output) | $0.435 / $0.87 | $3.00 / $15.00 |

## Category Breakdown

### Agentic

- Winner: Kimi K3
- DeepSeek V4 Pro 0813 public-lane score: 56.1 (Supported · #37/151)
- Kimi K3 public-lane score: 71.9 (Supported · #4/151)

| Benchmark | DeepSeek V4 Pro 0813 | Kimi K3 | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 67.9% | 88.3% | Kimi K3 |
| Terminal-Bench 2.1 | 87.9% | Coming soon | Coming soon |
| BrowseComp | 83.4% | 91.2% | Kimi K3 |
| HLE w/ tools | 60.0% | Coming soon | Coming soon |
| MCP Atlas | 73.6% | 84.2% | Kimi K3 |
| Toolathlon | 51.8% | Coming soon | Coming soon |
| CyberGym | 83.3% | Coming soon | Coming soon |
| Toolathlon-Verified | 74.1% | 73.2% | DeepSeek V4 Pro 0813 |
| Agents' Last Exam | 25.7% | Coming soon | Coming soon |
| AutomationBench | 31.8% | 30.8% | DeepSeek V4 Pro 0813 |
| Terminal-Bench 2.1 (Vals) | 54.7% | 80.9% | Kimi K3 |
| DeepSearchQA | Coming soon | 95.0% | Coming soon |
| JobBench | Coming soon | 52.9% | Coming soon |
| APEX-Agents | Coming soon | 37.6% | Coming soon |
| SpreadsheetBench 2 | Coming soon | 34.8% | Coming soon |
| DECK-Bench | Coming soon | 73.5% | Coming soon |

### Coding

- Winner: Kimi K3
- DeepSeek V4 Pro 0813 public-lane score: 52.2 (Supported · #58/183)
- Kimi K3 public-lane score: 68 (Supported · #7/183)

| Benchmark | DeepSeek V4 Pro 0813 | Kimi K3 | Winner |
|-----------|-----------|-----------|--------|
| LiveCodeBench Pass@1-COT | 93.5% | Coming soon | Coming soon |
| Codeforces | 3206.0 | Coming soon | Coming soon |
| SWE-bench Verified | 80.6% | Coming soon | Coming soon |
| SWE-bench Pro | 55.4% | Coming soon | Coming soon |
| SWE Multilingual | 76.2% | Coming soon | Coming soon |
| Terminal-Bench 2.0 | 67.9% | Coming soon | Coming soon |
| Vibe Code Bench | 49.93% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 87.9% | Coming soon | Coming soon |
| NL2Repo | 61.5% | Coming soon | Coming soon |
| deepSwe | 62.7% | 67.5% | Kimi K3 |
| DSBench-FullStack | 71.1% | Coming soon | Coming soon |
| DSBench-Hard | 67.2% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 87.5% | 87.2% | DeepSeek V4 Pro 0813 |
| SWE-bench (Vals) | 96.4% | 93.4% | DeepSeek V4 Pro 0813 |
| cursorBench32 | Coming soon | 60.8% | Coming soon |
| FrontierSWE | Coming soon | 81.2% | Coming soon |
| ProgramBench | Coming soon | 77.8% | Coming soon |
| Kimi Code Bench v2 | Coming soon | 72.9% | Coming soon |
| sweMarathon | Coming soon | 42% | Coming soon |
| PostTrain Bench | Coming soon | 36.6% | Coming soon |
| MLS-Bench Lite | Coming soon | 48.3% | Coming soon |
| VulcanBench v3 | Coming soon | 73.7% | Coming soon |
| OpenHarmony Bench | Coming soon | 57.3% | Coming soon |
| FrontierSWE v2 | Coming soon | 25.9% | Coming soon |

### Multimodal & Grounded

- Winner: Coming soon
- DeepSeek V4 Pro 0813 public-lane score: Coming soon
- Kimi K3 public-lane score: 89.5 (#1/48)

| Benchmark | DeepSeek V4 Pro 0813 | Kimi K3 | Winner |
|-----------|-----------|-----------|--------|
| OfficeQA Pro | Coming soon | 63.3% | Coming soon |
| MMMU-Pro | Coming soon | 81.6% | Coming soon |
| MMMU-Pro w/ Python | Coming soon | 83.4% | Coming soon |
| CharXiv w/o tools | Coming soon | 84.8% | Coming soon |
| CharXiv | Coming soon | 91.3% | Coming soon |
| MathVision | Coming soon | 94.3% | Coming soon |
| MathVision w/ Python | Coming soon | 97.8% | Coming soon |
| BabyVision w/ Python | Coming soon | 85.7% | Coming soon |
| ZeroBench | Coming soon | 23.0% | Coming soon |
| ZeroBench w/ Python | Coming soon | 41.0% | Coming soon |
| WorldVQA ForceAnswer | Coming soon | 51.0% | Coming soon |
| OmniDocBench | Coming soon | 91.1% | Coming soon |
| PerceptionBench | Coming soon | 58.5% | Coming soon |

### Reasoning

- Winner: Coming soon
- DeepSeek V4 Pro 0813 public-lane score: 58.7 (#18/22)
- Kimi K3 public-lane score: 78.5 (#3/22)

| Benchmark | DeepSeek V4 Pro 0813 | Kimi K3 | 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: 60.9 (Estimated · #37/181)
- Kimi K3 public-lane score: 72.3 (Supported · #8/181)

| Benchmark | DeepSeek V4 Pro 0813 | Kimi K3 | 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% | 93.5% | Kimi K3 |
| GPQA-D | 90.1% | 93.5% | Kimi K3 |
| HLE | 42.7% | 56% | Kimi K3 |
| GPQA Diamond (Vals) | 92.4% | 92.9% | Kimi K3 |
| MMLU-Pro (Vals) | 87.0% | 88.0% | Kimi K3 |
| HLE w/o tools | Coming soon | 43.5% | Coming soon |

### Mathematics

- Winner: Coming soon
- DeepSeek V4 Pro 0813 public-lane score: 80.4 (Unranked · 4 rankable rows)
- Kimi K3 public-lane score: Coming soon

| Benchmark | DeepSeek V4 Pro 0813 | Kimi K3 | Winner |
|-----------|-----------|-----------|--------|
| HMMT Feb 2026 | 95.2% | Coming soon | Coming soon |
| IMOAnswerBench | 89.8% | Coming soon | Coming soon |
| Apex | 38.3% | Coming soon | Coming soon |
| Apex Shortlist | 90.2% | Coming soon | Coming soon |

## FAQ

### Which is better overall, DeepSeek V4 Pro 0813 or Kimi K3?

Kimi K3 is ahead overall on BenchLM right now.

### Where is the biggest gap between DeepSeek V4 Pro 0813 and Kimi K3?

The widest category gap is in reasoning, where the averages are 58.7 for DeepSeek V4 Pro 0813 and 78.5 for Kimi K3.

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

DeepSeek V4 Pro 0813 currently has 39 sourced benchmark scores on BenchLM.

### How many benchmarks does Kimi K3 cover on BenchLM?

Kimi K3 currently has 43 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 K3 vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-kimi-k3)
- [DeepSeek V4 Pro 0813 vs GPT-6 Astra](/compare/deepseek-v4-pro-0813-vs-gpt-6-astra)
- [Kimi K3 vs GPT-6 Astra](/compare/gpt-6-astra-vs-kimi-k3)

## Explore More

- [DeepSeek V4 Pro 0813 profile](/models/deepseek-v4-pro-0813)
- [Kimi K3 profile](/models/kimi-k3)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)