# DeepSeek V4 Flash 0731

DeepSeek · Open Weight · bench-align-v5

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelscale.dev/models/deepseek-v4-flash-max  
JSON: https://modelscale.dev/api/model/deepseek-v4-flash-max

## Facts

| Field | Value | Evidence |
| --- | --- | --- |
| Canonical id | `deepseek-v4-flash-max` | — |
| Overall score | Unavailable | Unavailable · source benchlm:models |
| Context window | 1M tokens | Observed 2026-10-23 · source benchlm:models |
| Release date | 2026-07-31 | Observed 2026-10-23 · source benchlm:models |
| Access type | Open Weight | — |
| Blended $/1M (75% input / 25% output) | $0.18 | Derived from the input and output rates below |
| Cost per successful task (LiveBench) | $0.0596 | Last good 2026-10-08 · source livebench:cost |

## Capability evidence

Seven axes from the ranking source. An axis the source did not score is unavailable, not zero.

| Axis | Score | Evidence |
| --- | --- | --- |
| Agentic | 54.4 | Observed 2026-10-23 · source benchlm:models |
| Coding | 55.5 | Observed 2026-10-23 · source benchlm:models |
| Knowledge | 66.2 | Observed 2026-10-23 · source benchlm:models |
| Reasoning | 60.8 | Observed 2026-10-23 · source benchlm:models |
| Multimodal & Grounded | Unavailable | Unavailable · source benchlm:models |
| Instruction Following | Unavailable | Unavailable · source benchlm:models |
| Math | 87.1 | Observed 2026-10-23 · source benchlm:models |

## Runtime service evidence

Measured values with the date they were observed. Nothing is inferred from a sibling model or a provider claim. Regional or per-endpoint measurements appear only when the API supplies them; none are modelled.

| Measurement | Value | Observed | Last good | Evidence |
| --- | --- | --- | --- | --- |
| Time to first token | 12.61 s | 2026-10-23 | 2026-10-23 | Observed 2026-10-23 · source benchlm:speed |
| Throughput | 174 tok/s | 2026-10-23 | 2026-10-23 | Observed 2026-10-23 · source benchlm:speed |

## Endpoint and price matrix

Every published price component, including cache reads and writes.

| Component | USD | Evidence |
| --- | --- | --- |
| Input / 1M tokens | $0.14 | Observed 2026-10-23 · source benchlm:pricing |
| Output / 1M tokens | $0.28 | Observed 2026-10-23 · source benchlm:pricing |
| Cache read / 1M tokens | $0.0028 | Observed 2026-10-23 · source benchlm:pricing |
| Cache write / 1M tokens | Unavailable | Unavailable · source openrouter:pricing |
| Blended / 1M (75% input / 25% output) | $0.18 | Derived — from the input and output rates above; it has no source record of its own |
| Cost per successful task (LiveBench) | $0.0596 | Last good 2026-10-08 · source livebench:cost |

**Self-hosted listing.** Historical. DeepSeek V4 Flash 0731 used the shared `deepseek-v4-flash` API ID at $0.14 cache-miss input / $0.0028 cache-hit input / $0.28 output per million tokens; BenchLM represents the model at its highest published reasoning effort. DeepSeek retired the V4 Flash SKU on September 10, 2026 when it launched DeepSeek-V4.1-Flash as `deepseek-flash`; the legacy `deepseek-v4-flash` ID is still accepted but temporarily routes to V4.1 Flash and bills at the V4.1 Flash rate. The rates stored here are historical: the last standalone V4 Flash figures BenchLM recorded from the pricing page checked August 12, 2026, before DeepSeek's peak/off-peak schedule took effect at 16:00 UTC on August 16, 2026. The rates above are a hosted price matched from another provider, not a first-party list price.

## Workload-aware monthly cost example

10 conversations per day × 8 messages × 22 active days, 1200 input and 400 output tokens per message, no cache. Derived here from the published rates above by this site's own calculator — not a figure any source published.

| Field | Value |
| --- | --- |
| Modelled monthly cost | $0.49 |
| Modelled tokens | 2.82M |

## Benchmark record

57 matched benchmark rows with their published value, unit, and provenance.

### Knowledge

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| GPQA (Graduate-Level Google-Proof Q&A) | 88.1 | 448 questions | Graduate level | [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://arxiv.org/abs/2311.12022) |
| GPQA-D (GPQA Diamond) | 88.1 | Graduate-level science questions | Graduate level | [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://arxiv.org/abs/2311.12022) |
| MMLU-Pro (Massive Multitask Language Understanding Professional) | 86.2 | Multiple subjects | Professional level | [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://arxiv.org/abs/2406.01574) |
| HLE (Humanity's Last Exam) | 34.8 | Expert-level questions | Frontier expert level | [Humanity's Last Exam](https://lastexam.ai/) |
| Artificial Analysis Intelligence Index | 34.3 | Cross-benchmark intelligence index | Display-only external reference | [Artificial Analysis](https://artificialanalysis.ai/) |
| AA-GPQA Diamond (Artificial Analysis GPQA Diamond) | 90.8 | Graduate-level science questions | Graduate-level science reasoning | [Artificial Analysis GPQA Diamond Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/gpqa-diamond) |
| AA-HLE (Artificial Analysis Humanity's Last Exam) | 38.6 | Expert-level questions | Frontier expert reasoning | [Artificial Analysis Humanity's Last Exam Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/hle) |
| AA-Omniscience Index (Artificial Analysis Omniscience Index) | -14.3 | Knowledge questions | Broad factual knowledge | [AA-Omniscience: Knowledge and Hallucination Benchmark](https://artificialanalysis.ai/evaluations/omniscience) |
| AA-Omniscience Accuracy (Artificial Analysis Omniscience Accuracy) | 40.4 | Knowledge questions | Broad knowledge | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| AA-Omniscience Hallucination Rate (Artificial Analysis Omniscience Hallucination Rate) | 91.7 | Knowledge questions | Factuality | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| SimpleQA (Measuring Short-Form Factuality in Large Language Models) | 34.1 | Factual questions | Factual accuracy focused | [Measuring short-form factuality in large language models](https://arxiv.org/abs/2411.04368) |
| Chinese-SimpleQA | 78.9 | Chinese factual questions | Factual accuracy focused | [DeepSeek-V4 Technical Report](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main/DeepSeek_V4.pdf) |
| GPQA Diamond (Vals) (GPQA Diamond, Vals AI run) | 89.9 | Graduate-level science questions | Expert reasoning | [Vals AI GPQA Diamond, Vals AI run leaderboard](https://www.vals.ai/benchmarks/gpqa) |
| MMLU-Pro (Vals) (MMLU-Pro, Vals AI run) | 86.2 | Academic multiple-choice questions | Broad academic knowledge | [Vals AI MMLU-Pro, Vals AI run leaderboard](https://www.vals.ai/benchmarks/mmlu_pro) |

### Coding

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| Terminal-Bench 2.1 | 82.7 | Terminal-based software-agent tasks | Professional software engineering | [Terminal-Bench](https://www.tbench.ai/) |
| Codeforces (Codeforces Rating) | 3052.0 | Competitive programming contests | Elite competitive programming | [DeepSeek-V4 Technical Report](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main/DeepSeek_V4.pdf) |
| Terminal-Bench 2.0 | 56.9 | Terminal-based software tasks | Professional software engineering | [Terminal-Bench 2.0](https://www.tbench.ai/) |
| SWE-bench Verified (Software Engineering Benchmark Verified) | 79 | 500 verified issues | Professional software engineering | [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://arxiv.org/abs/2310.06770) |
| LiveCodeBench Pass@1-COT (LiveCodeBench Pass@1 with Chain-of-Thought) | 91.6 | DeepSeek-V4 report evaluation window | Competitive programming level | [DeepSeek-V4 technical report](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/resolve/main/DeepSeek_V4.pdf?download=true) |
| SWE-bench Pro | 52.6 | 1,865 repository problems | Long-horizon professional engineering | [SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?](https://arxiv.org/abs/2509.16941) |
| VulcanBench v3 | 88.4 | 23 post-cutoff repository tasks in the v3 report | Professional multi-file software engineering | [VulcanBench](https://github.com/morganlinton/VulcanBench/tree/main) |
| OpenHarmony Bench (OpenHarmony Bench v1.0) | 53.8 | 153 app-development and bug-fix tasks | End-to-end OpenHarmony application development | [OpenHarmony Bench: Evaluating LLMs and Coding Agents on OpenHarmony App Development](https://arxiv.org/abs/2608.16022) |
| SWE Multilingual | 73.3 | Multilingual software-engineering tasks | Professional software engineering | [MiniMax M2.7: Early Echoes of Self-Evolution](https://www.minimax.io/news/minimax-m27-en) |
| NL2Repo | 54.2 | Natural language to repository tasks | System-level software comprehension | [MiniMax M2.7: Early Echoes of Self-Evolution](https://www.minimax.io/news/minimax-m27-en) |
| DSBench-FullStack (DeepSeek DSBench FullStack) | 68.7 | Internal full-stack coding-agent tasks | Full-stack software engineering | [DeepSeek V4 Flash 0731 update](https://api-docs.deepseek.com/zh-cn/updates/) |
| DSBench-Hard (DeepSeek DSBench Hard) | 59.6 | Internal hard coding-agent tasks | Advanced coding-agent challenges | [DeepSeek V4 Flash 0731 update](https://api-docs.deepseek.com/zh-cn/updates/) |
| AA Coding Index (Artificial Analysis Coding Index) | 69.1 | Cross-benchmark coding index | Display-only external reference | [Artificial Analysis model leaderboards](https://artificialanalysis.ai/leaderboards/models) |
| AA-SciCode (Artificial Analysis SciCode) | 50.3 | Scientific coding subproblems | Scientific programming | [Artificial Analysis SciCode Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/scicode) |
| LiveCodeBench (Vals) (LiveCodeBench, Vals AI run) | 87.3 | Competitive programming problems (easy, medium, hard) | Frontier coding | [Vals AI LiveCodeBench, Vals AI run leaderboard](https://www.vals.ai/benchmarks/lcb) |
| SWE-bench (Vals) (SWE-bench, Vals AI run) | 88.8 | Real repository issues by human time bucket | Frontier coding agents | [Vals AI SWE-bench, Vals AI run leaderboard](https://www.vals.ai/benchmarks/swebench) |
| DeepSWE | 54.4 | 113 software engineering tasks across 91 repositories and 5 languages | Long-horizon software engineering | [DeepSWE benchmark blog](https://deepswe.datacurve.ai/blog) |

### Mathematics

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| HMMT Feb 2026 (Harvard-MIT Mathematics Tournament February 2026) | 94.8 | Competition math problems | Olympiad-style mathematics | [Qwen3.6 launch benchmarks](https://qwen.ai/blog?id=qwen3.6) |
| IMOAnswerBench | 88.4 | Advanced mathematical answer generation | Olympiad-level mathematics | [DeepSeek-V4 Technical Report](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main/DeepSeek_V4.pdf) |
| Apex | 33.0 | Advanced mathematical reasoning | Frontier math reasoning | [DeepSeek-V4 Technical Report](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main/DeepSeek_V4.pdf) |
| Apex Shortlist | 85.7 | Advanced mathematical reasoning | Frontier math reasoning | [DeepSeek-V4 Technical Report](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main/DeepSeek_V4.pdf) |

### Reasoning

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| ARC-AGI-1 (ARC-AGI-1 Semi-Private Evaluation) | 89.00 | Semi-private ARC-AGI-1 evaluation set | Abstract visual reasoning | [ARC Prize leaderboard](https://arcprize.org/) |
| MRCR 1M | 78.7 | Million-token retrieval | Million-token long context | [DeepSeek-V4 Technical Report](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main/DeepSeek_V4.pdf) |
| CorpusQA 1M | 60.5 | Million-token corpus question answering | Million-token long context | [DeepSeek-V4 Technical Report](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main/DeepSeek_V4.pdf) |
| ARC-AGI-2 (Abstraction and Reasoning Corpus for AGI v2) | 61.388889 | Visual pattern completion and abstract reasoning | Expert-level — hardest public reasoning benchmark | [ARC-AGI-2: A Harder General Intelligence Benchmark](https://arcprize.org/arc-agi/2/) |
| AA-LCR (Artificial Analysis Long Context Reasoning) | 79.7 | Long-context reasoning tasks | Long-context reasoning | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| CritPt (Critical Physics Tasks) | 16.6 | Research-level physics questions | Research-level physics reasoning | [CritPt Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/critpt) |

### Agentic

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| Terminal-Bench 2.0 | 56.9 | Terminal-based software tasks | Professional software engineering | [Terminal-Bench 2.0](https://www.tbench.ai/) |
| Terminal-Bench 2.1 | 82.7 | Terminal-based software-agent tasks | Professional software engineering | [Terminal-Bench](https://www.tbench.ai/) |
| BrowseComp | 73.2 | Research questions requiring browsing | Hard web research | [BrowseComp](https://openai.com/index/browsecomp/) |
| HLE w/ tools (Humanity's Last Exam with tools) | 45.1 | Expert questions with tool use | Frontier tool-augmented reasoning | [DeepSeek-V4 Technical Report](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main/DeepSeek_V4.pdf) |
| GDPval-AA | 1189 | Agentic real-world work tasks | Professional agentic workflows | [DeepSeek-V4 Technical Report](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main/DeepSeek_V4.pdf) |
| GDPval-AA (GDPval-AA normalized) | 46.7 | Economically valuable tasks | Professional agentic workflows | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| AA Agentic Index (Artificial Analysis Agentic Index) | 41.7 | Cross-benchmark agentic index | Display-only external reference | [Artificial Analysis model leaderboards](https://artificialanalysis.ai/leaderboards/models) |
| CyberGym | 76.7 | 1,507 vulnerability analysis instances | Real-world cybersecurity | [CyberGym: Evaluating AI Agents' Real-World Cybersecurity Capabilities at Scale](https://www.cybergym.io/) |
| MCP Atlas | 69 | Tool-integrated agent tasks | Advanced tool use | [Introducing GPT-5.4 mini and nano](https://openai.com/index/introducing-gpt-5-4-mini-and-nano/) |
| Toolathlon | 47.8 | Multi-tool workflows | Advanced tool use | [Introducing GPT-5.4 mini and nano](https://openai.com/index/introducing-gpt-5-4-mini-and-nano/) |
| Toolathlon-Verified | 70.3 | Verified multi-tool workflows | Advanced tool use | [Kimi K3: Open Frontier Intelligence](https://www.kimi.com/blog/kimi-k3) |
| AutomationBench | 25.1 | 600 public automation tasks | Long-horizon automation | [Kimi K3: Open Frontier Intelligence](https://www.kimi.com/blog/kimi-k3) |
| Agents' Last Exam | 25.2 | Agent tasks | Advanced agentic work | [DeepSeek V4 Flash 0731 update](https://api-docs.deepseek.com/zh-cn/updates/) |
| Terminal-Bench 2.1 (Vals) (Terminal-Bench 2.1, Vals AI run) | 67.0 | Difficult terminal tasks | Frontier agentic | [Vals AI Terminal-Bench 2.1, Vals AI run leaderboard](https://www.vals.ai/benchmarks/terminal-bench-2-1) |
| MazeBench (MazeBench: visual spatial reasoning in a 3D open world) | 0 | 100 hidden gems across 256 rooms in one open world | Long-horizon spatial planning, with single puzzles that can take over one hundred moves | [MazeBench Results](https://mazebench.com/blog?post=maze-bench-results) |

### Multimodal & Grounded

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| Design Arena Website (Design Arena Website Elo) | 1208 | Website generation comparisons | Design and website generation | [OpenRouter Grok 4.3 benchmarks](https://openrouter.ai/x-ai/grok-4.3/benchmarks) |

## Lifecycle and limitations log

Lifecycle events the source associates with this model.

No lifecycle event references this model. That is not evidence the model has no lifecycle plan — only that this source published none.

## What this profile does not claim

Values are reproduced exactly as their sources published them, in the units those sources declared; none are converted, interpolated, or averaged across providers. Any field marked unavailable was attempted and not returned. Last attempted fetch for this model's score: 2026-10-23 13:17 UTC.