# DeepSeek V2-0628

DeepSeek V2-0628 is an AI model released by DeepSeek on Jun 28 2024. It has 236B parameters, a 128k context window and open weight.

## Facts

| Field | Value |
| --- | --- |
| Model | DeepSeek V2-0628 |
| Developer | DeepSeek |
| Release date | Friday, Jun 28 2024 |
| Licensing | Open Weight |
| Parameters | 236B |
| Context window | 128k |

## Tracked benchmark scores

| Benchmark | Score | Source | What it measures |
| --- | --- | --- | --- |
| HumanEval | 84.76% | Lab | 164 small Python problems: the AI is given a function's description and has to write the working function. This was the coding benchmark of the GPT-3.5 and GPT-4 era, before the field moved to fixing real bugs in real repositories. Higher is better. |
| MATH | 71.02% | Lab | accuracy on the original competition mathematics test set |

## About DeepSeek V2-0628

DeepSeek V2-0628 updated the chat API on June 28, 2024. DeepSeek reported improvements in programming, mathematics and reasoning, alongside changes to role-playing behavior.

The checkpoint later became one of the inputs to V2.5, which combined its conversational abilities with Coder V2-0724. The scores here use the June announcement's HumanEval and MATH evaluations, preserving their original measurements.

## Questions and answers

### When was DeepSeek V2-0628 released?

DeepSeek V2-0628 was released by DeepSeek on Friday, Jun 28 2024.

### Who made DeepSeek V2-0628?

DeepSeek V2-0628 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 V2-0628 get?

DeepSeek V2-0628 reports 2 tracked benchmark scores — HumanEval: 84.76%; MATH: 71.02%. Tracked scores may come from lab reports or independent benchmarks; source details accompany the benchmark data.

### What is the context window of DeepSeek V2-0628?

DeepSeek V2-0628 has a context window of 128k. Providers may specify separate input and output token limits.

### How many parameters does DeepSeek V2-0628 have?

DeepSeek V2-0628 is reported at 236B parameters.

### Is DeepSeek V2-0628 open source?

Partly. DeepSeek V2-0628 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 V2-0628?

DeepSeek's previous tracked release was DeepSeek Coder V2 on Jun 14 2024, 14 days earlier. It was followed by DeepSeek Coder V2-0724 on Jul 24 2024.


---

Canonical page: https://aireleasetracker.com/model/deepseek/deepseek-v2-0628
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.
