Skip to main content

DeepSeekLanguage model

DeepSeek V4 Flash 0731

DeepSeek V4 Flash 0731 has no overall index value yet because there are too few independent benchmark results.

PopularityRank 245 of 785

42out of 100-4 vs. last month

based on search, usage and attention

Summary

DeepSeek V4 Flash 0731 is the dated V4-Flash checkpoint from July 31, 2026. Its model card lists MIT, very long context, and a recommended maximum output of 384,000 tokens at the higher reasoning levels. The date separates it from the current deepseek-flash route.

DeepSeek-V4.1-Flash is the current API reference; DeepSeek V4 Flash 0731 remains the concrete 0731 artifact.

See for yourself: one prompt, one attempt

We show the latest attempt without fixes; it does not count toward the overall index.

The response reached the token limit. No complete recording is available.

Pelican on a bicycle

Prompt

Generate an SVG of a pelican riding a bicycle

Oct 2, 2026 · 123 s · $0.0011

Not yet visually reviewed. A successful recording does not confirm correct physics or full compliance with the prompt.

Test details
Run date
Oct 2, 2026
API provider
openrouter
Requested API model
deepseek/deepseek-v4-flash-0731
Reasoning setting
high
Token limit including reasoning
8,192 tokens
Output tokens
8,192 tokens
Cost of the attempt
$0.0011
Response time
123.2 s
API model reported in response
deepseek/deepseek-v4-flash-0731
Pinned endpoint
StreamLake | deepseek/deepseek-v4-flash-20260731
Temperature
Provider default
Test protocol
community-visual-tests-v1
Technical checks
Failed

Earlier attempts (1)

  • Oct 1, 2026API request failedReasoning setting: high
Task origin: Simon Willison
SVG short test

SVG short test

One SVG task with the same fixed settings for every model, without hidden thinking.

DeepSeek V4 Flash 0731

No independent test. This API route aliases deepseek-v4-flash.

All benchmark results

Every published result with its source, test setup and comparison models.

Show all 310 published benchmark results

Page 1 of 26

Measurements without matching peer values

These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.

BioMysteryBench: Hard (Show measurement, test conditions, and source)
Source value
23.529
Score
23.529
Metric
accuracy
Unit
%
Benchmark version
1
Category
general
Task
human_difficult
Task label
Hard
Direction
Higher is better
Source type
independent-evaluator
Evaluator
Vals AI
Status
active
Retrieved at
2026-11-07
Methodology
Source model ID: deepseek/deepseek-v4-flash-0731. Source model name: DeepSeek V4 Flash 0731. Provider reported by source: DeepSeek. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-11-05. Harness: Terminus 2. Reasoning effort: high. Maximum output tokens: 384000. Latency in seconds: 1622.715. Standard error: 3.396. Cost per task in USD: 0.062194. Source ID: vals-ai. Evidence capture ID: vals-biomysterybench-2026-11-07-c2992129e13e. Source payload hash: c2992129e13e1455796b51fe354f18fa049ad9dcfe02fd66196230a60aeea9df. Parser version: vals-astro-v4. Imported at: 2026-11-07. Source cohort: vals-biomysterybench:1:human_difficult
Comparison methodology
Harness: Terminus 2. Reasoning effort: high. Maximum output tokens: 384000
Source Vals AI
BioMysteryBench: Human-solvable (Show measurement, test conditions, and source)
Source value
73.973
Score
73.973
Metric
accuracy
Unit
%
Benchmark version
1
Category
general
Task
human_solvable
Task label
Human-solvable
Direction
Higher is better
Source type
independent-evaluator
Evaluator
Vals AI
Status
active
Retrieved at
2026-11-07
Methodology
Source model ID: deepseek/deepseek-v4-flash-0731. Source model name: DeepSeek V4 Flash 0731. Provider reported by source: DeepSeek. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-11-05. Harness: Terminus 2. Reasoning effort: high. Maximum output tokens: 384000. Latency in seconds: 1622.715. Standard error: 1.37. Cost per task in USD: 0.033211. Source ID: vals-ai. Evidence capture ID: vals-biomysterybench-2026-11-07-c2992129e13e. Source payload hash: c2992129e13e1455796b51fe354f18fa049ad9dcfe02fd66196230a60aeea9df. Parser version: vals-astro-v4. Imported at: 2026-11-07. Source cohort: vals-biomysterybench:1:human_solvable
Comparison methodology
Harness: Terminus 2. Reasoning effort: high. Maximum output tokens: 384000
Source Vals AI
BioMysteryBench: Overall (Show measurement, test conditions, and source)
Source value
64.444
Score
64.444
Metric
accuracy
Unit
%
Benchmark version
1
Category
general
Task
overall
Task label
Overall
Direction
Higher is better
Source type
independent-evaluator
Evaluator
Vals AI
Status
active
Retrieved at
2026-11-07
Methodology
Source model ID: deepseek/deepseek-v4-flash-0731. Source model name: DeepSeek V4 Flash 0731. Provider reported by source: DeepSeek. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-11-05. Harness: Terminus 2. Reasoning effort: high. Maximum output tokens: 384000. Latency in seconds: 1622.715. Standard error: 1.283. Cost per task in USD: 0.038768. Source ID: vals-ai. Evidence capture ID: vals-biomysterybench-2026-11-07-c2992129e13e. Source payload hash: c2992129e13e1455796b51fe354f18fa049ad9dcfe02fd66196230a60aeea9df. Parser version: vals-astro-v4. Imported at: 2026-11-07. Source cohort: vals-biomysterybench:1:overall
Comparison methodology
Harness: Terminus 2. Reasoning effort: high. Maximum output tokens: 384000
Source Vals AI
Code Migration: CLI (Show measurement, test conditions, and source)
Source value
31.985
Score
31.985
Metric
accuracy
Unit
%
Benchmark version
1
Category
coding
Task
cli
Task label
CLI
Direction
Higher is better
Source type
independent-evaluator
Evaluator
Vals AI
Status
active
Retrieved at
2026-11-07
Methodology
Source model ID: deepseek/deepseek-v4-flash-0731. Source model name: DeepSeek V4 Flash 0731. Provider reported by source: DeepSeek. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-10-29. Reasoning effort: high. Maximum output tokens: 384000. Latency in seconds: 9130.856. Standard error: 2.386. Cost per task in USD: 4.627483. Source ID: vals-ai. Evidence capture ID: vals-code-migration-2026-11-07-23c368426e3e. Source payload hash: 23c368426e3e145dbba17219be86d157ba6ebf3b5c25c8f7ba2d5723986fb9b1. Parser version: vals-astro-v4. Imported at: 2026-11-07. Source cohort: vals-code-migration:1:cli
Comparison methodology
Reasoning effort: high. Maximum output tokens: 384000
Source Vals AI
Code Migration: COBOL (Show measurement, test conditions, and source)
Source value
58.571
Score
58.571
Metric
accuracy
Unit
%
Benchmark version
1
Category
coding
Task
cobol
Task label
COBOL
Direction
Higher is better
Source type
independent-evaluator
Evaluator
Vals AI
Status
active
Retrieved at
2026-11-07
Methodology
Source model ID: deepseek/deepseek-v4-flash-0731. Source model name: DeepSeek V4 Flash 0731. Provider reported by source: DeepSeek. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-10-29. Reasoning effort: high. Maximum output tokens: 384000. Latency in seconds: 3409.251. Standard error: 16. Cost per task in USD: 0.541149. Source ID: vals-ai. Evidence capture ID: vals-code-migration-2026-11-07-23c368426e3e. Source payload hash: 23c368426e3e145dbba17219be86d157ba6ebf3b5c25c8f7ba2d5723986fb9b1. Parser version: vals-astro-v4. Imported at: 2026-11-07. Source cohort: vals-code-migration:1:cobol
Comparison methodology
Reasoning effort: high. Maximum output tokens: 384000
Source Vals AI
Code Migration: Overall (Show measurement, test conditions, and source)
Source value
38.631
Score
38.631
Metric
accuracy
Unit
%
Benchmark version
1
Category
coding
Task
overall
Task label
Overall
Direction
Higher is better
Source type
independent-evaluator
Evaluator
Vals AI
Status
active
Retrieved at
2026-11-07
Methodology
Source model ID: deepseek/deepseek-v4-flash-0731. Source model name: DeepSeek V4 Flash 0731. Provider reported by source: DeepSeek. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-10-29. Reasoning effort: high. Maximum output tokens: 384000. Latency in seconds: 7700.455. Standard error: 4.382. Cost per task in USD: 3.605899. Source ID: vals-ai. Evidence capture ID: vals-code-migration-2026-11-07-23c368426e3e. Source payload hash: 23c368426e3e145dbba17219be86d157ba6ebf3b5c25c8f7ba2d5723986fb9b1. Parser version: vals-astro-v4. Imported at: 2026-11-07. Source cohort: vals-code-migration:1:overall
Comparison methodology
Reasoning effort: high. Maximum output tokens: 384000
Source Vals AI
CorpFin v2: Exact Pages (Show measurement, test conditions, and source)
Source value
60.839
Score
60.839
Metric
accuracy
Unit
%
Benchmark version
2
Category
finance
Task
exact_pages
Task label
Exact Pages
Direction
Higher is better
Source type
independent-evaluator
Evaluator
Vals AI
Status
active
Retrieved at
2026-11-07
Methodology
Source model ID: deepseek/deepseek-v4-flash-0731. Source model name: DeepSeek V4 Flash 0731. Provider reported by source: DeepSeek. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-08-12. Reasoning effort: high. Maximum output tokens: 384000. Latency in seconds: 9.468. Standard error: 1.666. Cost per task in USD: 0.000488. Source ID: vals-ai. Evidence capture ID: vals-corp_fin_v2-2026-11-07-8922bfb9f0b1. Source payload hash: 8922bfb9f0b175f7a8c108b1ef87048d17bf820216373dfcc42a276c1832f33f. Parser version: vals-astro-v4. Imported at: 2026-11-07. Source cohort: vals-corp-fin-v2:2:exact_pages
Comparison methodology
Reasoning effort: high. Maximum output tokens: 384000
Source Vals AI
CorpFin v2: Max Fitting Context (Show measurement, test conditions, and source)
Source value
62.704
Score
62.704
Metric
accuracy
Unit
%
Benchmark version
2
Category
finance
Task
max_fitting_context
Task label
Max Fitting Context
Direction
Higher is better
Source type
independent-evaluator
Evaluator
Vals AI
Status
active
Retrieved at
2026-11-07
Methodology
Source model ID: deepseek/deepseek-v4-flash-0731. Source model name: DeepSeek V4 Flash 0731. Provider reported by source: DeepSeek. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-08-12. Reasoning effort: high. Maximum output tokens: 384000. Latency in seconds: 22.531. Standard error: 1.651. Cost per task in USD: 0.02548. Source ID: vals-ai. Evidence capture ID: vals-corp_fin_v2-2026-11-07-8922bfb9f0b1. Source payload hash: 8922bfb9f0b175f7a8c108b1ef87048d17bf820216373dfcc42a276c1832f33f. Parser version: vals-astro-v4. Imported at: 2026-11-07. Source cohort: vals-corp-fin-v2:2:max_fitting_context
Comparison methodology
Reasoning effort: high. Maximum output tokens: 384000
Source Vals AI
CorpFin v2: Overall (Show measurement, test conditions, and source)
Source value
61.849
Score
61.849
Metric
accuracy
Unit
%
Benchmark version
2
Category
finance
Task
overall
Task label
Overall
Direction
Higher is better
Source type
independent-evaluator
Evaluator
Vals AI
Status
active
Retrieved at
2026-11-07
Methodology
Source model ID: deepseek/deepseek-v4-flash-0731. Source model name: DeepSeek V4 Flash 0731. Provider reported by source: DeepSeek. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-08-12. Reasoning effort: high. Maximum output tokens: 384000. Latency in seconds: 16.477. Standard error: 0.957. Cost per task in USD: 0.011801. Source ID: vals-ai. Evidence capture ID: vals-corp_fin_v2-2026-11-07-8922bfb9f0b1. Source payload hash: 8922bfb9f0b175f7a8c108b1ef87048d17bf820216373dfcc42a276c1832f33f. Parser version: vals-astro-v4. Imported at: 2026-11-07. Source cohort: vals-corp-fin-v2:2:overall
Comparison methodology
Reasoning effort: high. Maximum output tokens: 384000
Source Vals AI
CorpFin v2: Shared Max Context (Show measurement, test conditions, and source)
Source value
62.005
Score
62.005
Metric
accuracy
Unit
%
Benchmark version
2
Category
finance
Task
shared_max_context
Task label
Shared Max Context
Direction
Higher is better
Source type
independent-evaluator
Evaluator
Vals AI
Status
active
Retrieved at
2026-11-07
Methodology
Source model ID: deepseek/deepseek-v4-flash-0731. Source model name: DeepSeek V4 Flash 0731. Provider reported by source: DeepSeek. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-08-12. Reasoning effort: high. Maximum output tokens: 384000. Latency in seconds: 17.433. Standard error: 1.657. Cost per task in USD: 0.009434. Source ID: vals-ai. Evidence capture ID: vals-corp_fin_v2-2026-11-07-8922bfb9f0b1. Source payload hash: 8922bfb9f0b175f7a8c108b1ef87048d17bf820216373dfcc42a276c1832f33f. Parser version: vals-astro-v4. Imported at: 2026-11-07. Source cohort: vals-corp-fin-v2:2:shared_max_context
Comparison methodology
Reasoning effort: high. Maximum output tokens: 384000
Source Vals AI
CyberBench v1.1: Overall (Show measurement, test conditions, and source)
Source value
72.084
Score
72.084
Metric
accuracy
Unit
%
Benchmark version
1.1
Category
cybersecurity
Task
overall
Task label
Overall
Direction
Higher is better
Source type
independent-evaluator
Evaluator
Vals AI
Status
active
Retrieved at
2026-11-07
Methodology
Source model ID: deepseek/deepseek-v4-flash-0731. Source model name: DeepSeek V4 Flash 0731. Provider reported by source: DeepSeek. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-11-05. Reasoning effort: high. Maximum output tokens: 384000. Latency in seconds: 927.815. Standard error: 5.408. Cost per task in USD: 0.19286. Source ID: vals-ai. Evidence capture ID: vals-cyber-2026-11-07-cc5fe09bf1f8. Source payload hash: cc5fe09bf1f8c926613f8893f823a902fb33f219303590d6a2794e43708d67a5. Parser version: vals-astro-v4. Imported at: 2026-11-07. Source cohort: vals-cyberbench:1.1:overall
Comparison methodology
Reasoning effort: high. Maximum output tokens: 384000
Source Vals AI
CyberBench v1.1: Patch (Show measurement, test conditions, and source)
Source value
87.5
Score
87.5
Metric
accuracy
Unit
%
Benchmark version
1.1
Category
cybersecurity
Task
patch
Task label
Patch
Direction
Higher is better
Source type
independent-evaluator
Evaluator
Vals AI
Status
active
Retrieved at
2026-11-07
Methodology
Source model ID: deepseek/deepseek-v4-flash-0731. Source model name: DeepSeek V4 Flash 0731. Provider reported by source: DeepSeek. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-11-05. Reasoning effort: high. Maximum output tokens: 384000. Latency in seconds: 606.957. Standard error: 4.419. Cost per task in USD: 0.105488. Source ID: vals-ai. Evidence capture ID: vals-cyber-2026-11-07-cc5fe09bf1f8. Source payload hash: cc5fe09bf1f8c926613f8893f823a902fb33f219303590d6a2794e43708d67a5. Parser version: vals-astro-v4. Imported at: 2026-11-07. Source cohort: vals-cyberbench:1.1:patch
Comparison methodology
Reasoning effort: high. Maximum output tokens: 384000
Source Vals AI

Page 1 of 26

Popularity compared

How often the model is searched for, used and mentioned, compared with every model of its category.

Popularity index

The 100 most popular models of this category, 0 to 100, higher is more popular

20 of 101 models

GPT-6 Astra83
Claude Haiku 5.577
GPT-6 Sol73
GPT-573
DeepSeek V4.1 Flash 101769
Claude Opus 5.568
Qwen 3.8 27B68
Grok 4.767
Kimi K367
Qwen 3.8 Max 090266
Claude Sonnet 564
Qwen3.5 4B64
DeepSeek-V4-Flash64
Claude Fable 5.164
GPT-5.6 Terra64
MiniCPM-V 4.7 35B-A3B63
GPT-6.1 Sol63
Claude Opus 563
Qwen 3.8 Flash62
DeepSeek V4 Flash 073142

As of November 2026 · Source: gradually.ai popularity index

Over time

Weekly values from October 18, 2026 to November 7, 2026

DeepSeek V4 Flash 0731K2 Horizon 375B-A23B 42Command R 42GLM-4.5V 42Ling 3.1 Flash 42

Method changes in the timeline, a jump at these points is no market event:

  1. 1November 1, 2026: Value only with search or usage data, 30-day attention

What is gaining popularity right now, across models, vendors, harnesses and AI subscriptions, is collected in All AI trends.

Similar models

More models of the same kind as DeepSeek V4 Flash 0731, chosen by model line, developer, size, price and release date.

All specifications

Architecture

Parameters
284 billion
Source: Parameters
Active parameters
13 billion
Source: Active parameters
Knowledge cutoff
May 2025
Source: Knowledge cutoff

Input and output

Context window
1,000,000 tokens
Source: Context window
Maximum output
384,000 tokens
Source: Maximum output
Inputs
Text
Source: Inputs
Outputs
Text
Source: Outputs
Reasoning
Yes
Source: Reasoning
Tool calling
Yes
Source: Tool calling

Watermarking and provenance

AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.

AI watermarking
Unknown
no source
Watermarking technique
Not known
no source

Licence and access

Weights
Open weights
Source: Weights
Access
API
Source: Access
License
MIT
Source: License

Prices

No DeepSeek subscription includes this model. Through other providers from $6 a month (Token Plan Individual Lite, with limited credits). 12 plans in Germany.

Filter plans
PlanMonthly list priceNote
Token Plan Individual LiteAlibaba Cloud (Qwen)$6with limited credit
Poe Basic$4.99with limited credit
Token Plan Individual EssentialAlibaba Cloud (Qwen)$10with limited credit
Token Plan Individual StandardAlibaba Cloud (Qwen)$18with limited credit
Token Plan Team Standard SeatAlibaba Cloud (Qwen)$20with limited credit, for teams, per seat
Poe Plus$19.99with limited credit
Poe Pro$49.99with limited credit
Token Plan Individual ProAlibaba Cloud (Qwen)$68with limited credit
Token Plan Team Pro SeatAlibaba Cloud (Qwen)$75with limited credit, for teams, per seat
Poe Advanced$99.99with limited credit
Token Plan Team Max SeatAlibaba Cloud (Qwen)$200with limited credit, for teams, per seat
Poe Max$249.99with limited credit

All plans in the AI subscription comparison

Frequently asked questions about DeepSeek V4 Flash 0731

What is the knowledge cutoff of DeepSeek V4 Flash 0731?

May 2025, according to DeepSeek. That is 14 months before release.

Stated by DeepSeek

How large is the context window of DeepSeek V4 Flash 0731?

1 M tokens. That is how much text DeepSeek V4 Flash 0731 reads at once, about 1,500 A4 pages.

Page count as a rule of thumb from Artificial Analysis

Context windowTokens the model reads at once · higher is better
DeepSeek V4 Flash 0731Rank 31 of 1031M
Claude Opus 5.51M
Gemini 4 Carbon1M
Claude Fable 5.11M
Claude Sonnet 5.51M
Muse Wonder Full1M
Claude Opus 51M

Can I run DeepSeek V4 Flash 0731 locally?

Yes, the weights are open. With 284B parameters it needs a lot of memory, more a server than a laptop.

Stated by DeepSeek

Open weights
yes
License
MIT
Parameters
284B
active per token
13B

Where can I use DeepSeek V4 Flash 0731?

Not in a DeepSeek subscription. Including other providers that makes 12 plans in Germany.

Subscription comparison, prices in Germany incl. VAT

At DeepSeek

No DeepSeek subscription includes this model.

Through other providers

12 plans from 2 providers, from $6 a month (Token Plan Individual Lite), with limited credits.

Sources and data date

Show all 42 sources

Benchmark sources at a glance

Which independent evaluators tested this model. This is coverage, not a quality ranking.

EvaluatorTest seriesComposite indicesRecorded active measurements
Vals AI240182

Without vendor claims and historical or disputed results; those stay labelled in the single values.

TypeEvidence and data date
Input

Documented modalities. Retrieved October 27, 2026.

Source: models.dev catalog · models.dev catalog (retrieved October 27, 2026) · DeepSeek model catalog snapshot · Editorial description reviewed October 2, 2026
Output

Documented modalities. Retrieved October 27, 2026.

Source: models.dev catalog · models.dev catalog (retrieved October 27, 2026) · DeepSeek model catalog snapshot · Editorial description reviewed October 2, 2026
Research statusResearch date October 15, 2026. 7 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Not published

agent-evaluation-setup

Note

The official table gives exact 0731 release scores but does not expose the agent framework, reasoning effort, decoding settings, quantization, or task run date.

Additional sourceHugging Face (retrieved October 15, 2026) · DeepSeek V4 Flash 0731 model card · Editorial description reviewed October 2, 2026
Additional sourceVals AI (retrieved November 7, 2026)12345678910111213141516171819
Additional sourceVals AI (retrieved October 16, 2026; November 7, 2026)1234
Additional sourceVals AI (retrieved October 16, 2026)
Additional sourceVals AI (retrieved October 16, 2026; October 31, 2026; November 7, 2026)
Additional sourceVals AI (retrieved October 16, 2026; October 30, 2026; October 31, 2026)
Additional sourceVals AI (retrieved August 11, 2026; October 16, 2026)
Additional sourceParallel Search Capability Leaderboard (retrieved October 18, 2026)
Additional sourceTowards AI ToneBench (retrieved October 19, 2026; October 28, 2026; October 30, 2026)
Additional sourceARC Prize Verified Results (retrieved October 23, 2026)
Additional sourceAlman Institut (retrieved November 6, 2026)
Additional sourceModel metadata (retrieved October 18, 2026)
Additional sourceModel metadata (retrieved November 6, 2026)
Additional sourceDeepSeek V4.1 lifecycle notice · Editorial description reviewed October 2, 2026
Additional sourceOpenRouter: Popularity index (derived), CC BY 4.0
Additional sourceVercel AI Gateway: Popularity index (derived), CC BY 4.0
Additional sourceOllama: cumulative downloads for the popularity index
Additional sourceReplicate: cumulative runs for the popularity index
Additional sourceGoogle Trending Now: limited feed selection for Germany and the US
Additional sourceCreative Commons Attribution 4.0