# DeepSeek-V4.1-Flash-1017

DeepSeek-V4.1-Flash-1017 is an AI model released by DeepSeek on Oct 17 2026. It has open weight. Tracked results include 68.2% on NL2Repo-Bench, 60.5% on AutomationBench and 77% on DeepSWE 1.1.

## Facts

| Field | Value |
| --- | --- |
| Model | DeepSeek-V4.1-Flash-1017 |
| Developer | DeepSeek |
| Release date | Saturday, Oct 17 2026 |
| Licensing | Open Weight |

## Tracked benchmark scores

| Benchmark | Score | Source | What it measures |
| --- | --- | --- | --- |
| DeepSWE 1.1 | 77% | Lab | Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. (Version 1.1 of the test.) Higher is better. |
| NL2Repo-Bench | 68.2% | Lab | Tests whether the AI can turn a natural-language requirement into working code across an entire repository, not just produce a single function or patch. Higher is better. |
| Terminal-Bench 4.0 | 42.3% | Lab | Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Version 4.0 recalibrated how much time, CPU and memory each task gets, removed eight tasks and fixed nineteen, so fewer runs fail for reasons that have nothing to do with the model. Scores are not comparable with earlier versions. Higher is better. |
| Humanity's Last Exam (no tools) | 42.6% | Lab | Humanity's Last Exam — extremely hard expert questions across many subjects, written so you can't just look up the answer. “No tools” means the AI answers on its own. Higher is better. |
| Agent's Last Exam (pass@1) | 35.4% | Lab | A hard set of desktop and operating-system tasks an AI agent has to finish by looking at the screen and working the machine itself. The score is the share it passes outright — partial credit does not count. Higher is better. |
| AutomationBench | 60.5% | Lab | Tests whether the AI can run real multi-step business workflows — the kind of end-to-end office processes companies want to automate — from start to finish. Higher is better. |
| Chartography (with tools) | 83% | Lab | A chart-centred test run with tools available to the AI, reported separately from the chart-reading benchmarks above it. Higher is better. |

## Questions and answers

### When was DeepSeek-V4.1-Flash-1017 released?

DeepSeek-V4.1-Flash-1017 was released by DeepSeek on Saturday, Oct 17 2026.

### Who made DeepSeek-V4.1-Flash-1017?

DeepSeek-V4.1-Flash-1017 was built by DeepSeek. Chinese AI lab known for efficient, open-weight models. Gained attention for strong performance at lower cost.

### What benchmark scores did DeepSeek-V4.1-Flash-1017 get?

DeepSeek-V4.1-Flash-1017 reports 7 tracked benchmark scores — DeepSWE 1.1: 77%; NL2Repo-Bench: 68.2%; Terminal-Bench 4.0: 42.3%; Humanity's Last Exam (no tools): 42.6%; Agent's Last Exam (pass@1): 35.4%; AutomationBench: 60.5%; Chartography (with tools): 83%. Tracked scores may come from lab reports or independent benchmarks; source details accompany the benchmark data. It holds the best score among all models tracked here on NL2Repo-Bench and AutomationBench.

### Is DeepSeek-V4.1-Flash-1017 open source?

Partly. DeepSeek-V4.1-Flash-1017 is an open-weight model: the trained weights are free to download and run locally or on your own infrastructure, but the training data and code are not fully released and the license may restrict some commercial uses. It is not open source in the strict sense.

### What came before and after DeepSeek-V4.1-Flash-1017?

DeepSeek's previous tracked release was DeepSeek-V4.1-Flash on Sep 10 2026, 37 days earlier. It is the most recent DeepSeek model tracked on AI Release Tracker.


---

Canonical page: https://aireleasetracker.com/model/deepseek/deepseek-v4.1-flash-1017
Site index: https://aireleasetracker.com/llms.txt
Source: AI Release Tracker (https://aireleasetracker.com). Most benchmark scores come from lab launch material; gathered results identify the leaderboard that published them.