# DeepSeek V4 Flash 0731 vs GPT-5.4 mini

> Side-by-side benchmark comparison for DeepSeek V4 Flash 0731 and GPT-5.4 mini across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/deepseek-v4-flash-0731-vs-gpt-5-4-mini
- Last updated: September 27, 2026

- Shared sourced benchmarks: 12
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.7

## Quick Verdict

Pick DeepSeek V4 Flash 0731 if you want the stronger benchmark profile. GPT-5.4 mini only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- DeepSeek V4 Flash 0731 leads overall 57 to 55.01.
- The clearest category separation is in mathematics, where the averages are 79.9 for DeepSeek V4 Flash 0731 and 44.3 for GPT-5.4 mini.
- The biggest single benchmark swing is ARC-AGI-2 in Reasoning, with scores of 61.4% and 18.9%.
- DeepSeek V4 Flash 0731 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 | GPT-5.4 mini |
|----------|----------|----------|
| Creator | DeepSeek | OpenAI |
| Type | Open Weight | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 1M | 400K |
| Overall Score | null | 55.01 |
| Benchmarks Covered | 42 | 21 |
| Pricing (input/output) | $0.14 / $0.28 | $0.75 / $4.50 |

## Category Breakdown

### Agentic

- Winner: Not comparable
- DeepSeek V4 Flash 0731 public-lane score: Coming soon
- GPT-5.4 mini public-lane score: 33.9 (Supported · #59/105)

| Benchmark | DeepSeek V4 Flash 0731 | GPT-5.4 mini | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 56.9% | 60% | GPT-5.4 mini |
| BrowseComp | 73.2% | Coming soon | Coming soon |
| HLE w/ tools | 45.1% | Coming soon | Coming soon |
| MCP Atlas | 69% | 57.7% | DeepSeek V4 Flash 0731 |
| Toolathlon | 47.8% | 42.9% | DeepSeek V4 Flash 0731 |
| Terminal-Bench 2.1 | 82.7% | Coming soon | Coming soon |
| CyberGym | 76.7% | Coming soon | Coming soon |
| Toolathlon-Verified | 70.3% | Coming soon | Coming soon |
| Agents' Last Exam | 25.2% | Coming soon | Coming soon |
| AutomationBench | 25.1% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 67.0% | 54.7% | DeepSeek V4 Flash 0731 |
| OSWorld-Verified | Coming soon | 72.1% | Coming soon |
| τ²-bench results | Coming soon | 93.4% | Coming soon |

### Coding

- Winner: Not comparable
- DeepSeek V4 Flash 0731 public-lane score: Coming soon
- GPT-5.4 mini public-lane score: 37.2 (Supported · #65/135)

| Benchmark | DeepSeek V4 Flash 0731 | GPT-5.4 mini | Winner |
|-----------|-----------|-----------|--------|
| LiveCodeBench Pass@1-COT | 91.6% | Coming soon | Coming soon |
| Codeforces | 3052.0 | Coming soon | Coming soon |
| SWE-bench Verified | 79% | Coming soon | Coming soon |
| SWE-bench Pro | 52.6% | Coming soon | Coming soon |
| SWE Multilingual | 73.3% | Coming soon | Coming soon |
| Terminal-Bench 2.0 | 56.9% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 82.7% | Coming soon | Coming soon |
| NL2Repo | 54.2% | Coming soon | Coming soon |
| 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% | 81.5% | DeepSeek V4 Flash 0731 |
| SWE-bench (Vals) | 88.8% | 73.0% | DeepSeek V4 Flash 0731 |
| Vibe Code Bench | Coming soon | 47.97% | Coming soon |
| FrontierCode 1.1 Main | Coming soon | 27.0% | Coming soon |

### Reasoning

- Winner: Not comparable
- DeepSeek V4 Flash 0731 public-lane score: 57 (Unranked · 4 rankable rows)
- GPT-5.4 mini public-lane score: 39.9 (Unranked · 4 rankable rows)

| Benchmark | DeepSeek V4 Flash 0731 | GPT-5.4 mini | Winner |
|-----------|-----------|-----------|--------|
| MRCR 1M | 78.7% | Coming soon | Coming soon |
| CorpusQA 1M | 60.5% | Coming soon | Coming soon |
| ARC-AGI-1 | 89.00% | 63.70% | DeepSeek V4 Flash 0731 |
| ARC-AGI-2 | 61.4% | 18.9% | DeepSeek V4 Flash 0731 |

### Multimodal & Grounded

- Winner: Not comparable
- DeepSeek V4 Flash 0731 public-lane score: Coming soon
- GPT-5.4 mini public-lane score: 57.3 (#33/50)

| Benchmark | DeepSeek V4 Flash 0731 | GPT-5.4 mini | Winner |
|-----------|-----------|-----------|--------|
| MMMU-Pro | Coming soon | 76.6% | Coming soon |
| MMMU-Pro w/ Python | Coming soon | 78% | Coming soon |

### Knowledge

- Winner: Not comparable
- DeepSeek V4 Flash 0731 public-lane score: Coming soon
- GPT-5.4 mini public-lane score: 48.4 (Supported · #62/158)

| Benchmark | DeepSeek V4 Flash 0731 | GPT-5.4 mini | 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% | 88% | DeepSeek V4 Flash 0731 |
| GPQA-D | 88.1% | Coming soon | Coming soon |
| HLE | 34.8% | 41.5% | GPT-5.4 mini |
| GPQA Diamond (Vals) | 89.9% | 83.1% | DeepSeek V4 Flash 0731 |
| MMLU-Pro (Vals) | 86.2% | 84.6% | DeepSeek V4 Flash 0731 |
| HLE w/o tools | Coming soon | 28.2% | Coming soon |

### Instruction Following

- Winner: Not comparable
- DeepSeek V4 Flash 0731 public-lane score: Coming soon
- GPT-5.4 mini public-lane score: 88.5 (#24/124)

### Mathematics

- Winner: Not comparable
- DeepSeek V4 Flash 0731 public-lane score: 79.9 (Unranked · 4 rankable rows)
- GPT-5.4 mini public-lane score: 44.3 (Unranked · 2 rankable rows)

| Benchmark | DeepSeek V4 Flash 0731 | GPT-5.4 mini | Winner |
|-----------|-----------|-----------|--------|
| HMMT Feb 2026 | 94.8% | Coming soon | Coming soon |
| IMOAnswerBench | 88.4% | Coming soon | Coming soon |
| Apex | 33.0% | Coming soon | Coming soon |
| Apex Shortlist | 85.7% | Coming soon | Coming soon |
| FrontierMath v2 (Tiers 1-3) | Coming soon | 28.280% | Coming soon |
| FrontierMath v2 (Tier 4) | Coming soon | 2.080% | Coming soon |

## FAQ

### Which is better overall, DeepSeek V4 Flash 0731 or GPT-5.4 mini?

DeepSeek V4 Flash 0731 is ahead overall on BenchLM right now.

### Where is the biggest gap between DeepSeek V4 Flash 0731 and GPT-5.4 mini?

The widest category gap is in mathematics, where the averages are 79.9 for DeepSeek V4 Flash 0731 and 44.3 for GPT-5.4 mini.

### 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 GPT-5.4 mini cover on BenchLM?

GPT-5.4 mini currently has 21 sourced benchmark scores on BenchLM.

## Related Comparisons

- [DeepSeek V4 Flash 0731 vs GPT-5.4 Pro](/compare/deepseek-v4-flash-0731-vs-gpt-5-4-pro)
- [GPT-5.4 mini vs GPT-5.4 Pro](/compare/gpt-5-4-mini-vs-gpt-5-4-pro)
- [DeepSeek V4 Flash 0731 vs GPT-5.4](/compare/deepseek-v4-flash-0731-vs-gpt-5-4)
- [GPT-5.4 mini vs GPT-5.4](/compare/gpt-5-4-vs-gpt-5-4-mini)

## Explore More

- [DeepSeek V4 Flash 0731 profile](/models/deepseek-v4-flash-0731)
- [GPT-5.4 mini profile](/models/gpt-5-4-mini)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)