Model update · Capability and access

Mistral Large 4 arrives: drawings, code and ways to try it

The multimodal model opens an API preview. Connect its official drawing demo, coding results and independent index score with existing GLM, Kimi and Beam choices.

Access currently comes through the public API preview in Mistral Studio; the announced weights release is planned for the end of October.

Published Oct 7, 2026

Orange marks connect a parts list and section-view labels in Mistral’s official replay. — A frame from the official drawing replay. Labels, the parts list and local views supply the stated evidence; this is not an engineering conclusion generated or validated by BitShovel. · Open full-size image

In this articleContents3

中文

Point the question back to the drawing

Mistral announced the Large 4 public preview on October 6 as a trillion-parameter-scale general multimodal model. Its release materials emphasize coding, tool-based work and visual understanding, with drawing, chart and document demonstrations.

The drawing example starts with a question about whether two components touch, then checks the parts list, zooms into a section view and follows labels. The useful feature is a path from the question back to inspectable evidence. This is an official replay; independent work on the same task can extend that picture.

Open the official visual demo

Sources and further reading

Mistral Large 4 announcementOfficial · October 6, 2026Model positioning, official demonstrations and task charts.
Visual demo embedded in the announcementOfficial public replayA localization and drawing-inspection replay. Its data names the internal patchstral-sft-260921 model; it is not a BitShovel run of the current API.

中文

Task results and an overall index provide different references

Mistral reports 61.7% on DeepSWE 1.1, rounded to about 62 in its chart alongside GLM, Kimi and their tools. That concerns a specific coding task set; tool conditions and the self-reported entry belong with the scores.

Artificial Analysis currently displays 38 for Mistral Large 4 Preview. The table keeps the tested settings of several existing choices. It gives an approximate position; different settings do not imply equal compute, and index points are not success rates on drawings or Chinese tasks.

Artificial Analysis v4.3.2 · read October 7; displayed integer values.
Model and setting	Intelligence Index
GLM-5.3 · max	45
Kimi K3 · max	44
DeepSeek V4.1 Flash · max	39
Mistral Large 4 Preview · effort not specified in the source table	38

The DeepSWE 1.1 chart published by Mistral shows about 62 for Mistral Large 4 Preview, with tool conditions on the labels. — Original Mistral chart. The axis starts at 40, so read the numbers. Its footnote describes private results ahead of the harness release; Beam is self-reported, and the tool setups differ. · Open full-size image

Sources and further reading

Mistral Large 4 announcementOfficial · October 6, 2026Model positioning, official demonstrations and task charts.
Artificial Analysis model leaderboardIndependent evaluator · checked October 7Displayed integer scores from the same v4.3.2 index, with each configuration retained.

中文

Start through the API; follow the weights release separately

The current model card lists mistral-large-4 with 1M context, multimodal chat, document questions, tool calling and structured outputs. This is hosted access. End-of-month weights remain a plan, rather than a downloadable equivalent of today’s preview.

This connects to two existing threads. Beam also separates preview access from weights, while the GLM/Kimi Bedrock example shows how services and tools carry a model into work. Public outputs and revisions using matched material and tools are the next useful evidence.

Sources and further reading

Mistral Large 4 model cardOfficial documentation · checked October 7Public preview, model ID, context and current access conditions.
Mistral changelogOfficial · October 6 entryThe API preview is available; weights remain a later release.