# Mistral 7B v0.3

Mistral 7B v0.3 is an AI model released by Mistral on May 22 2024. It has 7B parameters, a 32k context window and open weight.

## Facts

| Field | Value |
| --- | --- |
| Model | Mistral 7B v0.3 |
| Developer | Mistral |
| Release date | Wednesday, May 22 2024 |
| Licensing | Open Weight |
| Parameters | 7B |
| Context window | 32k |

## Tracked benchmark scores

| Benchmark | Score | Source | What it measures |
| --- | --- | --- | --- |
| HumanEval | 38.4% | 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 | 13.2% | Lab | accuracy on the original competition mathematics test set |

## About Mistral 7B v0.3

Mistral 7B v0.3 was released on May 22, 2024 as a further update to Mistral's original compact language-model family. The release expanded the vocabulary and adopted the v3 tokenizer. Its instruction checkpoint added function calling, allowing an application to request structured tool invocations alongside ordinary text responses.

Mistral published base and instruction weights under Apache 2.0, retaining a 32K-token context. The function-calling interface made the instructed version useful as a local component in applications that connected a small model to external services. The benchmark results recorded here describe the instruction checkpoint, rather than the original September 2023 base model.

## Questions and answers

### When was Mistral 7B v0.3 released?

Mistral 7B v0.3 was released by Mistral on Wednesday, May 22 2024.

### Who made Mistral 7B v0.3?

Mistral 7B v0.3 was built by Mistral. French AI company building open and commercial models. Founded in 2023 by former Meta and DeepMind researchers.

### What benchmark scores did Mistral 7B v0.3 get?

Mistral 7B v0.3 reports 2 tracked benchmark scores — HumanEval: 38.4%; MATH: 13.2%. Tracked scores may come from lab reports or independent benchmarks; source details accompany the benchmark data.

### What is the context window of Mistral 7B v0.3?

Mistral 7B v0.3 has a context window of 32k. Providers may specify separate input and output token limits.

### How many parameters does Mistral 7B v0.3 have?

Mistral 7B v0.3 is reported at 7B parameters.

### Is Mistral 7B v0.3 open source?

Partly. Mistral 7B v0.3 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 Mistral 7B v0.3?

Mistral's previous tracked release was Mixtral 8×22B on Apr 10 2024, 42 days earlier. It was followed by Codestral 22B on May 29 2024.


---

Canonical page: https://aireleasetracker.com/model/mistral/mistral-7b-v0.3
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.
