# DeepSeek V4 Flash 0731 vs dots3-note Preview

> Side-by-side benchmark comparison for DeepSeek V4 Flash 0731 and dots3-note Preview across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/deepseek-v4-flash-0731-vs-dots3-note-preview
- Last updated: September 28, 2026

- Shared sourced benchmarks: 13
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.7

## Quick Verdict

Pick dots3-note Preview if you want the stronger benchmark profile. DeepSeek V4 Flash 0731 only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- dots3-note Preview leads overall 62.64 to 57.
- The clearest category separation is in reasoning, where the averages are 57 for DeepSeek V4 Flash 0731 and 72.9 for dots3-note Preview.
- The biggest single benchmark swing is ARC-AGI-2 in Reasoning, with scores of 61.4% and 81.4%.
- dots3-note Preview is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- DeepSeek V4 Flash 0731 also has the larger context window at 1M.

## Model Snapshot

| Property | DeepSeek V4 Flash 0731 | dots3-note Preview |
|----------|----------|----------|
| Creator | DeepSeek | Dots Studio |
| Type | Open Weight | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 1M | 512K |
| Overall Score | null | 62.64 |
| Benchmarks Covered | 42 | 31 |
| Pricing (input/output) | $0.14 / $0.28 | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Not comparable
- DeepSeek V4 Flash 0731 public-lane score: Coming soon
- dots3-note Preview public-lane score: 56.4 (Estimated · #28/117)

| Benchmark | DeepSeek V4 Flash 0731 | dots3-note Preview | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 56.9% | Coming soon | Coming soon |
| BrowseComp | 73.2% | 83.3% | dots3-note Preview |
| HLE w/ tools | 45.1% | 52.6% | dots3-note Preview |
| MCP Atlas | 69% | Coming soon | Coming soon |
| Toolathlon | 47.8% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 82.7% | 75.1% | DeepSeek V4 Flash 0731 |
| CyberGym | 76.7% | Coming soon | Coming soon |
| Toolathlon-Verified | 70.3% | 55.6% | DeepSeek V4 Flash 0731 |
| Agents' Last Exam | 25.2% | Coming soon | Coming soon |
| AutomationBench | 25.1% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 67.0% | Coming soon | Coming soon |
| Claw-Eval | Coming soon | 73.4% | Coming soon |
| skillsBench | Coming soon | 52.8% | Coming soon |
| APEX-Agents | Coming soon | 30.8% | Coming soon |
| DeepSearchQA | Coming soon | 92.1% | Coming soon |
| WideResearch | Coming soon | 78.9% | Coming soon |

### Coding

- Winner: Not comparable
- DeepSeek V4 Flash 0731 public-lane score: Coming soon
- dots3-note Preview public-lane score: Coming soon

| Benchmark | DeepSeek V4 Flash 0731 | dots3-note Preview | Winner |
|-----------|-----------|-----------|--------|
| LiveCodeBench Pass@1-COT | 91.6% | Coming soon | Coming soon |
| Codeforces | 3052.0 | 3056.0 | dots3-note Preview |
| SWE-bench Verified | 79% | 78.4% | DeepSeek V4 Flash 0731 |
| SWE-bench Pro | 52.6% | 61% | dots3-note Preview |
| SWE Multilingual | 73.3% | 75.7% | dots3-note Preview |
| Terminal-Bench 2.0 | 56.9% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 82.7% | 75.1% | DeepSeek V4 Flash 0731 |
| NL2Repo | 54.2% | 49.8% | DeepSeek V4 Flash 0731 |
| DeepSWE | 54.4% | Coming soon | Coming soon |
| DSBench-FullStack | 68.7% | Coming soon | Coming soon |
| DSBench-Hard | 59.6% | Coming soon | Coming soon |
| VulcanBench v3 | 88.4% | Coming soon | Coming soon |
| OpenHarmony Bench | 53.8% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 87.3% | Coming soon | Coming soon |
| SWE-bench (Vals) | 88.8% | Coming soon | Coming soon |
| LiveCodeBench v6 | Coming soon | 91.5% | Coming soon |

### Reasoning

- Winner: Not comparable
- DeepSeek V4 Flash 0731 public-lane score: 57 (Unranked · 4 rankable rows)
- dots3-note Preview public-lane score: 72.9 (Unranked · 1 rankable row)

| Benchmark | DeepSeek V4 Flash 0731 | dots3-note Preview | Winner |
|-----------|-----------|-----------|--------|
| MRCR 1M | 78.7% | Coming soon | Coming soon |
| CorpusQA 1M | 60.5% | Coming soon | Coming soon |
| ARC-AGI-1 | 89.00% | Coming soon | Coming soon |
| ARC-AGI-2 | 61.4% | 81.4% | dots3-note Preview |

### Multimodal & Grounded

- Winner: Not comparable
- DeepSeek V4 Flash 0731 public-lane score: Coming soon
- dots3-note Preview public-lane score: 67.2 (Unranked · 10 rankable rows)

| Benchmark | DeepSeek V4 Flash 0731 | dots3-note Preview | Winner |
|-----------|-----------|-----------|--------|
| SimpleVQA | Coming soon | 72.5% | Coming soon |
| MMMU-Pro | Coming soon | 79.1% | Coming soon |
| MathVision | Coming soon | 87.7% | Coming soon |
| ZeroBench | Coming soon | 19.0% | Coming soon |
| CharXiv w/o tools | Coming soon | 83.1% | Coming soon |
| GDP.pdf (no tools) | Coming soon | 60.7% | Coming soon |
| PerceptionBench | Coming soon | 53.4% | Coming soon |
| BabyVision | Coming soon | 50.0% | Coming soon |
| MMVU | Coming soon | 79.9% | Coming soon |
| VideoMMMU | Coming soon | 86.8% | Coming soon |

### Knowledge

- Winner: Not comparable
- DeepSeek V4 Flash 0731 public-lane score: Coming soon
- dots3-note Preview public-lane score: Coming soon

| Benchmark | DeepSeek V4 Flash 0731 | dots3-note Preview | Winner |
|-----------|-----------|-----------|--------|
| MMLU-Pro | 86.2% | Coming soon | Coming soon |
| SimpleQA | 34.1% | Coming soon | Coming soon |
| Chinese-SimpleQA | 78.9% | Coming soon | Coming soon |
| GPQA | 88.1% | Coming soon | Coming soon |
| GPQA-D | 88.1% | Coming soon | Coming soon |
| HLE | 34.8% | 52.6% | dots3-note Preview |
| GPQA Diamond (Vals) | 89.9% | Coming soon | Coming soon |
| MMLU-Pro (Vals) | 86.2% | Coming soon | Coming soon |

### Instruction Following

- Winner: Not comparable
- DeepSeek V4 Flash 0731 public-lane score: Coming soon
- dots3-note Preview public-lane score: 85.2 (#37/124)

| Benchmark | DeepSeek V4 Flash 0731 | dots3-note Preview | Winner |
|-----------|-----------|-----------|--------|
| IFBench | Coming soon | 80.4% | Coming soon |
| IFEval | Coming soon | 93.9% | Coming soon |

### Mathematics

- Winner: Not comparable
- DeepSeek V4 Flash 0731 public-lane score: 79.9 (Unranked · 4 rankable rows)
- dots3-note Preview public-lane score: Coming soon

| Benchmark | DeepSeek V4 Flash 0731 | dots3-note Preview | Winner |
|-----------|-----------|-----------|--------|
| HMMT Feb 2026 | 94.8% | Coming soon | Coming soon |
| IMOAnswerBench | 88.4% | 90.9% | dots3-note Preview |
| Apex | 33.0% | Coming soon | Coming soon |
| Apex Shortlist | 85.7% | Coming soon | Coming soon |

## FAQ

### Which is better overall, DeepSeek V4 Flash 0731 or dots3-note Preview?

dots3-note Preview is ahead overall on BenchLM right now.

### Where is the biggest gap between DeepSeek V4 Flash 0731 and dots3-note Preview?

The widest category gap is in reasoning, where the averages are 57 for DeepSeek V4 Flash 0731 and 72.9 for dots3-note Preview.

### How many benchmarks does DeepSeek V4 Flash 0731 cover on BenchLM?

DeepSeek V4 Flash 0731 currently has 42 sourced benchmark scores on BenchLM.

### How many benchmarks does dots3-note Preview cover on BenchLM?

dots3-note Preview currently has 31 sourced benchmark scores on BenchLM.

## Related Comparisons

- [DeepSeek V4 Flash 0731 vs GPT-6 Astra](/compare/deepseek-v4-flash-0731-vs-gpt-6-astra)
- [dots3-note Preview vs GPT-6 Astra](/compare/dots3-note-preview-vs-gpt-6-astra)
- [DeepSeek V4 Flash 0731 vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-deepseek-v4-flash-0731)
- [dots3-note Preview vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-dots3-note-preview)

## Explore More

- [DeepSeek V4 Flash 0731 profile](/models/deepseek-v4-flash-0731)
- [dots3-note Preview profile](/models/dots3-note-preview)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)