# DeepSeek-V4-Pro-0813

DeepSeek-V4-Pro-0813 is an AI model released by DeepSeek on Aug 13 2026. At release it scored 31.8% on AutomationBench, 87.9% on Terminal-Bench 2.1 and 74.1% on Toolathlon-Verified.

## Facts

| Field | Value |
| --- | --- |
| Model | DeepSeek-V4-Pro-0813 |
| Developer | DeepSeek |
| Release date | Thursday, Aug 13 2026 |
| Licensing | Proprietary |

## Benchmark scores published at release

| Benchmark | Score | What it measures |
| --- | --- | --- |
| Terminal-Bench 2.1 | 87.9% | Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better. |
| Toolathlon-Verified | 74.1% | Tests how well the AI uses everyday personal tools and apps to get things done — a human-checked version of Toolathlon. Higher is better. |
| CyberGym | 83.3% | Tests the AI on cybersecurity challenges — finding and exploiting software weaknesses inside a safe sandbox. Higher is better. |
| Humanity's Last Exam (no tools) | 42.7% | 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. |
| Humanity's Last Exam (with tools) | 60% | Humanity's Last Exam — extremely hard expert questions across many subjects. “With tools” means the AI is allowed to search the web or run code while answering. Higher is better. |
| AutomationBench | 31.8% | 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. |

## About DeepSeek-V4-Pro-0813

DeepSeek-V4-Pro-0813, released August 13, 2026, brought the top tier of the V4 line up to the agentic post-training that had landed on Flash two weeks earlier. On DeepSeek's own harness it scored 87.9 on Terminal-Bench 2.1, against 82.7 for V4-Flash-0731 and 72.1 for the April V4-Pro-Preview build, and 83.3 on CyberGym — the highest figure in the lab's launch comparison at the time, marginally ahead of Claude Fable 5. It also posted 42.7% on Humanity's Last Exam without tools and 60.0% with them, 74.1 on Toolathlon-Verified and 31.8 on the public AutomationBench split. As with the July Flash release, DeepSeek ran the code-agent evaluations through its own unreleased harness in minimal mode, and its numbers for rival models did not always match those labs' published figures, so the chart reads best as a within-family comparison.

The headline changes were operational rather than architectural. V4-Pro and V4-Flash both gained a selectable reasoning effort — low for simple prompts, high for everyday agent work, max for hard tasks — replacing the single fixed thinking budget of the earlier builds, and the release added native OpenAI Responses API support with one-click Codex setup. Distribution followed the pattern the Flash refresh established: the checkpoint reached the app and web product under an "Expert Mode" toggle and shipped through the API under unchanged model names, so existing callers were moved onto it without a code change. DeepSeek's launch post listed app, web, and API availability only, and announced no accompanying weight release.

## Questions and answers

### When was DeepSeek-V4-Pro-0813 released?

DeepSeek-V4-Pro-0813 was released by DeepSeek on Thursday, Aug 13 2026.

### Who made DeepSeek-V4-Pro-0813?

DeepSeek-V4-Pro-0813 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-Pro-0813 get?

DeepSeek-V4-Pro-0813 reports 6 tracked benchmark scores — Terminal-Bench 2.1: 87.9%; Toolathlon-Verified: 74.1%; CyberGym: 83.3%; Humanity's Last Exam (no tools): 42.7%; Humanity's Last Exam (with tools): 60%; AutomationBench: 31.8%. Scores are the figures published at release by DeepSeek. It holds the best score among all models tracked here on AutomationBench.

### Is DeepSeek-V4-Pro-0813 open source?

No. DeepSeek-V4-Pro-0813 is a proprietary model. The weights are not published — it is available only through the provider's own API, apps, or partner platforms.

### What came before and after DeepSeek-V4-Pro-0813?

DeepSeek's previous tracked release was DeepSeek-V4-Flash-0731 on Jul 31 2026, 13 days earlier. It is the most recent DeepSeek model tracked on AI Release Tracker.


---

Canonical page: https://aireleasetracker.com/model/deepseek/deepseek-v4-pro-0813
Full dataset: https://aireleasetracker.com/llms-full.txt · JSON: https://aireleasetracker.com/models.json
Source: AI Release Tracker (https://aireleasetracker.com). Benchmark scores are the figures published by the releasing lab at launch.