# DeepSeek V4 Pro vs Mistral Large 4

> Side-by-side benchmark comparison for DeepSeek V4 Pro and Mistral Large 4 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/deepseek-v4-pro-vs-mistral-large-4
- Last updated: November 21, 2026

- Shared sourced benchmarks: 4
- HTML indexing: indexable
- Ranking lane: BenchAlign v6.0

## Quick Verdict

DeepSeek V4 Pro leads by point estimate. Conditional score ranges do not establish rank confidence. Choose using the category evidence and your own workload tests.

## Summary

- DeepSeek V4 Pro has the higher overall point estimate 61.4 to 56.9. Conditional score ranges do not establish rank confidence.
- The clearest category separation is in knowledge, where the averages are 59.8 for DeepSeek V4 Pro and 48.1 for Mistral Large 4.
- The biggest single benchmark swing is Vibe Code Bench in Coding, with scores of 49.93% and 78.40%.
- Mistral Large 4 is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.

## Model Snapshot

| Property | DeepSeek V4 Pro | Mistral Large 4 |
|----------|----------|----------|
| Creator | DeepSeek | Mistral |
| Type | Open Weight | Open Weight |
| Reasoning | Reasoning | Hybrid |
| Context | 1M | 1M |
| Overall Score | 61.4 | 56.9 |
| Benchmarks Covered | 45 | 11 |
| Pricing (input/output) | $1.32 / $3.96 | $0.70 / $2.10 |

## Category Breakdown

### Agentic

- Winner: DeepSeek V4 Pro
- DeepSeek V4 Pro public-lane score: 59.3 (Supported · #60/179)
- Mistral Large 4 public-lane score: 56.2 (Supported · #74/179)

| Benchmark | DeepSeek V4 Pro | Mistral Large 4 | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 4.1 | 6.70% | 27.60% | Mistral Large 4 |
| Finch | 67.4% | 73.3% | Mistral Large 4 |
| Terminal-Bench 2.0 | 67.9% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 87.9% | Coming soon | Coming soon |
| BrowseComp | 83.4% | 84.5% | Mistral Large 4 |
| HLE w/ tools | 60.0% | Coming soon | Coming soon |
| MCP Atlas | 73.6% | Coming soon | Coming soon |
| Toolathlon | 51.8% | Coming soon | Coming soon |
| 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% | Coming soon | Coming soon |
| b3 Agent Security | Coming soon | 97.1% | Coming soon |
| Cyber Misuse Refusal | Coming soon | 96.6% | Coming soon |
| Cybench | Coming soon | 93.0% | Coming soon |
| Finance Agent v2 | Coming soon | 54.7% | Coming soon |
| CWE-bench | Coming soon | 45.6% | Coming soon |

### Coding

- Winner: Mistral Large 4
- DeepSeek V4 Pro public-lane score: 59.6 (Supported · #56/179)
- Mistral Large 4 public-lane score: 63.2 (Supported · #43/179)

| Benchmark | DeepSeek V4 Pro | Mistral Large 4 | 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% | 78.40% | Mistral Large 4 |
| 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 v1.0 | 59.0% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 87.5% | Coming soon | Coming soon |
| SWE-bench (Vals) | 96.4% | Coming soon | Coming soon |
| FrontierCode 2.0 | Coming soon | 19.7% | Coming soon |

### Reasoning

- Winner: DeepSeek V4 Pro
- DeepSeek V4 Pro public-lane score: 64.6 (Supported · #33/161)
- Mistral Large 4 public-lane score: 56 (Supported · #57/161)

| Benchmark | DeepSeek V4 Pro | Mistral Large 4 | Winner |
|-----------|-----------|-----------|--------|
| MRCR 1M | 83.5% | Coming soon | Coming soon |
| CorpusQA 1M | 62.0% | Coming soon | Coming soon |
| ARC-AGI-1 | 90.00% | Coming soon | Coming soon |
| ARC-AGI-2 | 61.3% | Coming soon | Coming soon |
| STEMBench | Coming soon | 2.50 | Coming soon |

### Multimodal & Grounded

- Winner: Directional only
- DeepSeek V4 Pro public-lane score: 60.6 (Estimated · #55/119)
- Mistral Large 4 public-lane score: 50.8 (Estimated · #77/119)

### Knowledge

- Winner: Directional only
- DeepSeek V4 Pro public-lane score: 59.8 (Supported · #46/158)
- Mistral Large 4 public-lane score: 48.1 (Estimated · #96/158)

| Benchmark | DeepSeek V4 Pro | Mistral Large 4 | Winner |
|-----------|-----------|-----------|--------|
| MMLU-Pro | 87.5% | Coming soon | Coming soon |
| Chinese-SimpleQA | 84.4% | Coming soon | Coming soon |
| GPQA | 90.1% | Coming soon | Coming soon |
| GPQA-D | 90.1% | Coming soon | Coming soon |
| HLE | 42.7% | Coming soon | Coming soon |
| GPQA Diamond (Vals) | 92.4% | Coming soon | Coming soon |
| MMLU-Pro (Vals) | 87.0% | Coming soon | Coming soon |

### Multilingual

- Winner: Not comparable
- DeepSeek V4 Pro public-lane score: 57.5 (Estimated · #31/87)
- Mistral Large 4 public-lane score: Coming soon

### Instruction Following

- Winner: Directional only
- DeepSeek V4 Pro public-lane score: 56.5 (Supported · #47/143)
- Mistral Large 4 public-lane score: 53.5 (Estimated · #62/143)

### Mathematics

- Winner: Directional only
- DeepSeek V4 Pro public-lane score: 59.4 (Supported · #34/125)
- Mistral Large 4 public-lane score: 55.5 (Estimated · #48/125)

| Benchmark | DeepSeek V4 Pro | Mistral Large 4 | 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 |
| FrontierMath v2 (Tiers 1-3) | 64.561% | Coming soon | Coming soon |
| FrontierMath v2 (Tier 4) | 26.829% | Coming soon | Coming soon |

## FAQ

### Which is better overall, DeepSeek V4 Pro or Mistral Large 4?

DeepSeek V4 Pro has the higher overall point estimate. Conditional score ranges do not establish rank confidence.

### Where is the biggest gap between DeepSeek V4 Pro and Mistral Large 4?

The widest category gap is in knowledge, where the averages are 59.8 for DeepSeek V4 Pro and 48.1 for Mistral Large 4.

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

DeepSeek V4 Pro currently has 45 sourced benchmark scores on BenchLM.

### How many benchmarks does Mistral Large 4 cover on BenchLM?

Mistral Large 4 currently has 11 sourced benchmark scores on BenchLM.

## Related Comparisons

- [DeepSeek V4 Pro vs Claude Fable 5.2](/compare/claude-fable-5-2-vs-deepseek-v4-pro)
- [Mistral Large 4 vs Claude Fable 5.2](/compare/claude-fable-5-2-vs-mistral-large-4)
- [DeepSeek V4 Pro vs Gemini 4 Neon](/compare/deepseek-v4-pro-vs-gemini-4-neon)
- [Mistral Large 4 vs Gemini 4 Neon](/compare/gemini-4-neon-vs-mistral-large-4)

## Explore More

- [DeepSeek V4 Pro profile](/models/deepseek-v4-pro)
- [Mistral Large 4 profile](/models/mistral-large-4)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)
