
DeepSeek · tested in Taskade Genesis
DeepSeek V4.1 Flash in Taskade
DeepSeek V4.1 Flash from DeepSeek runs on every plan, including Free. We last tested it on Oct 8, 2026 in TSK-1, our app-building test.
- Status
- Available
- Plan
- Every plan, including Free
- Where to pick it
- More models or All Models
- Your own key
- No
- Last test
- Context window
- 1Mtokens
- Max output
- 384Ktokens
- Released
- Knowledge cutoff
- Where it runs
- 14services
TSK-1 scorecard for the DeepSeek family
TSK Score
DeepSeek family, across real apps made in Taskade Genesis
- Interfaceready to share
- Leading
- Taskcompletes your task
- Strong
- Memorykeeps your data
- Strong
- Adapthandles follow-up edits
- Emerging
The richest app per shape among the economical models.
MoreLess
It built a six-page sales CRM whose scoring automation ran, a four-page match tracker, and a four-page cookbook with both automations live. On a family intake form it saved every answer and both photos.
Published scores
Benchmark scores that DeepSeek and test sites published for DeepSeek V4.1 Flash. Taskade did not re-run them. Lab-reported marks a score from DeepSeek itself.
| Benchmark | Score | Source |
|---|---|---|
| Terminal-Benchpass@1 · v2.1 · reasoning_effort=100 · DeepSeek Harness minimal modeHugging FaceLab-reported | 90.6% | Hugging FaceLab-reported |
| GPQA Diamondpass@1 · reasoning_effort=100Hugging FaceLab-reported | 90.9% | Hugging FaceLab-reported |
| Humanity's Last Exampass@1 · reasoning_effort=100 · full setHugging FaceLab-reported | 36.8% | Hugging FaceLab-reported |
More published scores (31)
| Benchmark | Score | Source |
|---|---|---|
| MathArena Apexpass@1 · reasoning_effort=100Hugging FaceLab-reported | 65.6% | Hugging FaceLab-reported |
| Humanity's Last Exampass@1 · reasoning_effort=100 · text-only subsetHugging FaceLab-reported | 39.1% | Hugging FaceLab-reported |
| Codeforcesrating · reasoning_effort=100Hugging FaceLab-reported | 3,471 | Hugging FaceLab-reported |
| Terminal-Benchpass@1 · v3.0 · reasoning_effort=100 · DeepSeek Harness minimal modeHugging FaceLab-reported | 30% | Hugging FaceLab-reported |
| Terminal-Benchpass@1 · v4.0 · reasoning_effort=100 · DeepSeek Harness minimal modeHugging FaceLab-reported | 31.2% | Hugging FaceLab-reported |
| DeepSWEresolved · v1.1 · reasoning_effort=100 · mini-swe-agentHugging FaceLab-reported | 74.2% | Hugging FaceLab-reported |
| ProgramBenchalmost@1 · reasoning_effort=100 · DeepSeek Harness minimal modeHugging FaceLab-reported | 20.3 | Hugging FaceLab-reported |
| NL2Reporeasoning_effort=100 · DeepSeek Harness minimal modeHugging FaceLab-reported | 64 | Hugging FaceLab-reported |
| CyberGympass@1 · reasoning_effort=100Hugging FaceLab-reported | 88.1% | Hugging FaceLab-reported |
| ExploitGympass@1 · reasoning_effort=100Hugging FaceLab-reported | 15.3% | Hugging FaceLab-reported |
| AutomationBenchpass@1 · reasoning_effort=100Hugging FaceLab-reported | 54.8% | Hugging FaceLab-reported |
| Agents' Last Exampass@1 · reasoning_effort=100Hugging FaceLab-reported | 31.8% | Hugging FaceLab-reported |
| SEC-Bench Propass@1 · reasoning_effort=100 · Claude CodeHugging FaceLab-reported | 62.8% | Hugging FaceLab-reported |
| Humanity's Last Exampass@1 · reasoning_effort=100; with toolsHugging FaceLab-reported | 63.9% | Hugging FaceLab-reported |
| Chartographypass@1 · reasoning_effort=100; with tools · Claude CodeHugging FaceLab-reported | 78.9% | Hugging FaceLab-reported |
| BabyVisionpass@1 · reasoning_effort=100; with tools · Claude CodeHugging FaceLab-reported | 89.6% | Hugging FaceLab-reported |
| ZeroBenchpass@5 · reasoning_effort=100; with tools · Claude Code · mainHugging FaceLab-reported | 49% | Hugging FaceLab-reported |
| DeepSWEresolved · v1.1 · reasoning_effort=100 · Claude CodeHugging FaceLab-reported | 69.8% | Hugging FaceLab-reported |
| Terminal-Benchpass@1 · v2.1 · reasoning_effort=100 · Claude CodeHugging FaceLab-reported | 88% | Hugging FaceLab-reported |
| DeepSWEresolved · v1.1 · reasoning_effort=100 · CodexHugging FaceLab-reported | 65.6% | Hugging FaceLab-reported |
| Terminal-Benchpass@1 · v2.1 · reasoning_effort=100 · CodexHugging FaceLab-reported | 84.1% | Hugging FaceLab-reported |
| DeepSWEresolved · v1.1 · reasoning_effort=100 · OpenCodeHugging FaceLab-reported | 65.5% | Hugging FaceLab-reported |
| Terminal-Benchpass@1 · v2.1 · reasoning_effort=100 · OpenCodeHugging FaceLab-reported | 85% | Hugging FaceLab-reported |
| DeepSWEresolved · v1.1 · reasoning_effort=100 · PiHugging FaceLab-reported | 66.2% | Hugging FaceLab-reported |
| Terminal-Benchpass@1 · v2.1 · reasoning_effort=100 · PiHugging FaceLab-reported | 86.1% | Hugging FaceLab-reported |
| Terminal-Benchpass@1 · v2.1 · reasoning_effort=100 · mini-swe-agentHugging FaceLab-reported | 90.3% | Hugging FaceLab-reported |
| DeepSWEresolved · v1.1 · reasoning_effort=100 · DeepSeek Harness minimal modeHugging FaceLab-reported | 72.6% | Hugging FaceLab-reported |
| DeepSWEresolved · v1.1 · reasoning_effort=100 · DeepSeek Harness standard modeHugging FaceLab-reported | 70.5% | Hugging FaceLab-reported |
| Terminal-Benchpass@1 · v2.1 · reasoning_effort=100 · DeepSeek Harness standard modeHugging FaceLab-reported | 85.8% | Hugging FaceLab-reported |
| DeepSWEresolved · v1.1 · reasoning_effort=100 · DeepSeek Harness PTC modeHugging FaceLab-reported | 67.6% | Hugging FaceLab-reported |
| Terminal-Benchpass@1 · v2.1 · reasoning_effort=100 · DeepSeek Harness PTC modeHugging FaceLab-reported | 85.8% | Hugging FaceLab-reported |
Scores collected by models.dev (MIT). Each source links the page that published the score.
Versions tested
Open a version to read its findings.
DeepSeek V4.1 FlashTested Oct 202612 findings
The richest app per shape among the economical models. It built a six-page sales CRM whose scoring automation ran, a four-page match tracker, and a four-page cookbook with both automations live. On a family intake form it saved every answer and both photos.
Built the richest sales CRM of the test, with six pages and a scoring automation that scored all 7 sample leads.
Built a four-page match tracker and said plainly that its weekly recap was still switched off.
Typed all 32 client sign-up questions and built a 48-field submissions table, then ran out of time before finishing.
Built a three-page fleet inspection app for 42 vans where the brief named 40.
Its recipe box came out as a printed cookbook with 13 recipes, four pages, and both automations live.
Built a three-page match tracker whose coaching automation ran on the first match logged and wrote a note back into that match about six minutes later.
Built a two-page family intake form that saved every answer and both photos, and its alert automation ran twice. The build ran past the 15-minute test limit.
Added the new teacher question and put the change live.
Built the family intake form in 7 minutes 25 seconds so it saved every answer and both photos, and its new-family automation ran. Three sample families showed on the teacher page as if they were real.
Added the new teacher question as an optional field and kept it off the printed facesheet, and said so.
Built a five-page Dota 2 match tracker with labeled sample matches, but every hero showed as unknown and no match could be saved, while its summary said the save had been checked.
Rebuilt the 32-question client sign-up form with all 32 questions word for word and a scoring rubric, but the form saved each answer one question off, so every submission was rejected.
Results by task
Model facts
The token limits are the most the model accepts. Taskade can run it with lower limits.
- Last updated
- Input types
- Text, Images
- Output types
- Text
- Reasoning
- Yes
- Tool calling
- Yes
- File attachments
- Yes
- Structured output
- Yes
- Open weights
- Yes
- Reasoning effort
- NoneLowHighMax
Published specs from the model maker, via models.dev (MIT).
Where it runs
Services outside Taskade that serve DeepSeek V4.1 Flash, from models.dev. Each link opens in a new tab.
How to choose DeepSeek V4.1 Flash
- In the builder chat, open the model menu and choose More models. Then pick the model.
- In the agent editor, pick the model under All Models.
- If your model menu does not show the model, Taskade uses TSK-Auto instead.
Where DeepSeek ranks
TSK Score out of 100.
Compare DeepSeek
Other DeepSeek models
FAQ
Which Taskade plans include DeepSeek V4.1 Flash?
DeepSeek V4.1 Flash runs in Taskade on every plan, including Free. If your model menu does not show it, Taskade uses TSK-Auto instead.
Has Taskade tested DeepSeek V4.1 Flash?
Yes. We last tested DeepSeek V4.1 Flash on Oct 8, 2026 in the TSK-1 Benchmark. The richest app per shape among the economical models. It built a six-page sales CRM whose scoring automation ran, a four-page match tracker, and a four-page cookbook with both automations live. On a family intake form it saved every answer and both photos.
How do I choose DeepSeek V4.1 Flash in Taskade?
In the builder chat, open the model menu and choose More models. Then pick DeepSeek V4.1 Flash. In the agent editor, pick it under All Models.
Who makes DeepSeek V4.1 Flash?
DeepSeek makes DeepSeek V4.1 Flash. Taskade runs it on every plan, including Free, beside frontier models from other top AI labs.