# DeepSeek V4.1 Flash 1017 vs DeepSeek V4 Pro

> Side-by-side benchmark comparison for DeepSeek V4.1 Flash 1017 and DeepSeek V4 Pro across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/deepseek-v4-1-flash-vs-deepseek-v4-pro
- Last updated: November 18, 2026

- Shared sourced benchmarks: 18
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

DeepSeek V4.1 Flash 1017 leads by point estimate. Conditional score ranges do not establish rank confidence. Choose using the category evidence and your own workload tests.

## Summary

- DeepSeek V4.1 Flash 1017 has the higher overall point estimate 63.94 to 62.71. Conditional score ranges do not establish rank confidence.
- The clearest category separation is in mathematics, where the averages are 64.4 for DeepSeek V4.1 Flash 1017 and 73.9 for DeepSeek V4 Pro.
- The biggest single benchmark swing is Codeforces in Coding, with scores of 3471.0 and 3206.0.
- DeepSeek V4.1 Flash 1017 is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.

## Model Snapshot

| Property | DeepSeek V4.1 Flash 1017 | DeepSeek V4 Pro |
|----------|----------|----------|
| Creator | DeepSeek | DeepSeek |
| Type | Open Weight | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 1M | 1M |
| Overall Score | 63.94 | 62.71 |
| Benchmarks Covered | 40 | 45 |
| Pricing (input/output) | $0.30 / $1.20 | $1.32 / $3.96 |

## Category Breakdown

### Agentic

- Winner: DeepSeek V4.1 Flash 1017
- DeepSeek V4.1 Flash 1017 public-lane score: 61.8 (Supported · #30/138)
- DeepSeek V4 Pro public-lane score: 57 (Supported · #41/138)

| Benchmark | DeepSeek V4.1 Flash 1017 | DeepSeek V4 Pro | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 4.1 | 38.50% | 6.70% | DeepSeek V4.1 Flash 1017 |
| Terminal-Bench 2.1 | 90.6% | 87.9% | DeepSeek V4.1 Flash 1017 |
| terminalBench3 | 30% | Coming soon | Coming soon |
| Terminal-Bench 4.0 | 42.30% | Coming soon | Coming soon |
| CyberGym | 88.1% | 83.3% | DeepSeek V4.1 Flash 1017 |
| ExploitGym | 15.3% | Coming soon | Coming soon |
| HLE w/ tools | 63.9% | 60.0% | DeepSeek V4.1 Flash 1017 |
| AutomationBench | 60.5% | 31.8% | DeepSeek V4.1 Flash 1017 |
| Agents' Last Exam | 35.4% | 25.7% | DeepSeek V4.1 Flash 1017 |
| Terminal-Bench 2.1 (Vals) | 74.5% | 54.7% | DeepSeek V4.1 Flash 1017 |
| CWE-bench v1 | 55.0% | Coming soon | Coming soon |
| MazeBench | 1% | Coming soon | Coming soon |
| CWE-bench | 57.6% | Coming soon | Coming soon |
| Finch | Coming soon | 67.4% | Coming soon |
| Terminal-Bench 2.0 | Coming soon | 67.9% | Coming soon |
| BrowseComp | Coming soon | 83.4% | Coming soon |
| MCP Atlas | Coming soon | 73.6% | Coming soon |
| Toolathlon | Coming soon | 51.8% | Coming soon |
| Toolathlon-Verified | Coming soon | 74.1% | Coming soon |

### Coding

- Winner: DeepSeek V4.1 Flash 1017
- DeepSeek V4.1 Flash 1017 public-lane score: 59.8 (Supported · #18/160)
- DeepSeek V4 Pro public-lane score: 51.4 (Supported · #41/160)

| Benchmark | DeepSeek V4.1 Flash 1017 | DeepSeek V4 Pro | Winner |
|-----------|-----------|-----------|--------|
| ScarfBench | 69.0% | Coming soon | Coming soon |
| Codeforces | 3471.0 | 3206.0 | DeepSeek V4.1 Flash 1017 |
| Terminal-Bench 2.1 | 90.6% | 87.9% | DeepSeek V4.1 Flash 1017 |
| terminalBench3 | 30% | Coming soon | Coming soon |
| DeepSWE | 77.0% | 62.7% | DeepSeek V4.1 Flash 1017 |
| ProgramBench | 29.1% | Coming soon | Coming soon |
| NL2Repo | 68.2% | 61.5% | DeepSeek V4.1 Flash 1017 |
| OpenHarmony Bench v1.0 | 60.3% | 59.0% | DeepSeek V4.1 Flash 1017 |
| Bug Hunt Bench | 39.1 fixes | Coming soon | Coming soon |
| FrontierCode 2.0 | 20.2% | Coming soon | Coming soon |
| CursorBench 4.0 | 47.7% | Coming soon | Coming soon |
| VulcanBench Frontier v4 | 88.7% | Coming soon | Coming soon |
| OpenHarmony Bench v1.2 | 71.28% | Coming soon | Coming soon |
| LiveCodeBench Pass@1-COT | Coming soon | 93.5% | Coming soon |
| SWE-bench Verified | Coming soon | 80.6% | Coming soon |
| SWE-bench Pro | Coming soon | 55.4% | Coming soon |
| SWE Multilingual | Coming soon | 76.2% | Coming soon |
| Terminal-Bench 2.0 | Coming soon | 67.9% | Coming soon |
| Vibe Code Bench | Coming soon | 49.93% | Coming soon |
| DSBench-FullStack | Coming soon | 71.1% | Coming soon |
| DSBench-Hard | Coming soon | 67.2% | Coming soon |
| LiveCodeBench (Vals) | Coming soon | 87.5% | Coming soon |
| SWE-bench (Vals) | Coming soon | 96.4% | Coming soon |

### Reasoning

- Winner: Directional only
- DeepSeek V4.1 Flash 1017 public-lane score: 60.4 (Estimated · #30/159)
- DeepSeek V4 Pro public-lane score: 58.1 (Supported · #33/159)

| Benchmark | DeepSeek V4.1 Flash 1017 | DeepSeek V4 Pro | Winner |
|-----------|-----------|-----------|--------|
| STEMBench | 2.54 | Coming soon | Coming soon |
| JevBench 1.4 | 4.77 | Coming soon | Coming soon |
| JevBench 1.5 | 6.65 | Coming soon | Coming soon |
| MRCR 1M | Coming soon | 83.5% | Coming soon |
| CorpusQA 1M | Coming soon | 62.0% | Coming soon |
| ARC-AGI-1 | Coming soon | 90.00% | Coming soon |
| ARC-AGI-2 | Coming soon | 61.3% | Coming soon |

### Multimodal & Grounded

- Winner: Not comparable
- DeepSeek V4.1 Flash 1017 public-lane score: 64 (Supported · #20/66)
- DeepSeek V4 Pro public-lane score: Coming soon

| Benchmark | DeepSeek V4.1 Flash 1017 | DeepSeek V4 Pro | Winner |
|-----------|-----------|-----------|--------|
| ExtractBench (LlamaIndex) | 87.11% | Coming soon | Coming soon |
| ParseBench-1 | 64.38% | Coming soon | Coming soon |
| Chartography (tools) | 83.0% | Coming soon | Coming soon |
| BabyVision w/ Python | 92.5% | Coming soon | Coming soon |
| ZeroBench w/ Python | 51.0% | Coming soon | Coming soon |

### Knowledge

- Winner: DeepSeek V4.1 Flash 1017
- DeepSeek V4.1 Flash 1017 public-lane score: 65.2 (Supported · #30/179)
- DeepSeek V4 Pro public-lane score: 64.2 (Supported · #35/179)

| Benchmark | DeepSeek V4.1 Flash 1017 | DeepSeek V4 Pro | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 90.9% | 90.1% | DeepSeek V4.1 Flash 1017 |
| GPQA-D | 90.9% | 90.1% | DeepSeek V4.1 Flash 1017 |
| HLE | 42.6% | 42.7% | DeepSeek V4 Pro |
| MMLU-Pro | Coming soon | 87.5% | Coming soon |
| Chinese-SimpleQA | Coming soon | 84.4% | Coming soon |
| GPQA Diamond (Vals) | Coming soon | 92.4% | Coming soon |
| MMLU-Pro (Vals) | Coming soon | 87.0% | Coming soon |

### Instruction Following

- Winner: Not comparable
- DeepSeek V4.1 Flash 1017 public-lane score: Coming soon
- DeepSeek V4 Pro public-lane score: 93.8 (#7/157)

### Mathematics

- Winner: Not comparable
- DeepSeek V4.1 Flash 1017 public-lane score: 64.4 (Unranked · 3 rankable rows)
- DeepSeek V4 Pro public-lane score: 73.9 (#4/13)

| Benchmark | DeepSeek V4.1 Flash 1017 | DeepSeek V4 Pro | Winner |
|-----------|-----------|-----------|--------|
| Apex | 65.6% | 38.3% | DeepSeek V4.1 Flash 1017 |
| FrontierMath v2 (Tiers 1-3) | 67.368% | 64.561% | DeepSeek V4.1 Flash 1017 |
| FrontierMath v2 (Tier 4) | 26.829% | 26.829% | Tie |
| HMMT Feb 2026 | Coming soon | 95.2% | Coming soon |
| IMOAnswerBench | Coming soon | 89.8% | Coming soon |
| Apex Shortlist | Coming soon | 90.2% | Coming soon |

## FAQ

### Which is better overall, DeepSeek V4.1 Flash 1017 or DeepSeek V4 Pro?

DeepSeek V4.1 Flash 1017 has the higher overall point estimate. Conditional score ranges do not establish rank confidence.

### Where is the biggest gap between DeepSeek V4.1 Flash 1017 and DeepSeek V4 Pro?

The widest category gap is in mathematics, where the averages are 64.4 for DeepSeek V4.1 Flash 1017 and 73.9 for DeepSeek V4 Pro.

### How many benchmarks does DeepSeek V4.1 Flash 1017 cover on BenchLM?

DeepSeek V4.1 Flash 1017 currently has 40 sourced benchmark scores on BenchLM.

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

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

## Related Comparisons

- [DeepSeek V4.1 Flash 1017 vs Claude Fable 5.2](/compare/claude-fable-5-2-vs-deepseek-v4-1-flash)
- [DeepSeek V4 Pro vs Claude Fable 5.2](/compare/claude-fable-5-2-vs-deepseek-v4-pro)
- [DeepSeek V4.1 Flash 1017 vs GPT-6.2 Astra](/compare/deepseek-v4-1-flash-vs-gpt-6-2-astra)
- [DeepSeek V4 Pro vs GPT-6.2 Astra](/compare/deepseek-v4-pro-vs-gpt-6-2-astra)

## Explore More

- [DeepSeek V4.1 Flash 1017 profile](/models/deepseek-v4-1-flash)
- [DeepSeek V4 Pro profile](/models/deepseek-v4-pro)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)
