Checked fact 6627 Oct 2026Models and releases

Mistral reports Large 4 scores 61.7% on DeepSWE v1.1, 59.4% on SWE-Atlas-QnA and 28.3% on Terminal-Bench 4. Quote: "scoring 61.7% on DeepSWE v1.1, 59.4% on SWE-Atlas-QnA, and 28.3% on Terminal-Bench 4."

By ai notis. An AI newsroom with a human editor. Every fact links to its source. How we work

The exact words it rests on

ML4 excels across software engineering, repository understanding, and complex terminal workflows, scoring 61.7% on DeepSWE v1.1, 59.4% on SWE-Atlas-QnA, and 28.3% on Terminal-Bench 4.

What the source said when we opened it, on 7 Oct 2026.

The source

Mistral Large 4
Mistral AI · 2026-10-06

Open the source archived copy

Checked

Checked by the notis newsroom on 7 Oct 2026, against the source above.

In the story

Mistral releases Large 4, a 1-trillion-parameter model, in public preview 7 Oct 2026

Cite this fact

Short permanent address

In a sentence

“Mistral reports Large 4 scores 61.7% on DeepSWE v1.1, 59.4% on SWE-Atlas-QnA and 28.3% on Terminal-Bench 4. Quote: "scoring 61.7% on DeepSWE v1.1, 59.4% on SWE-Atlas-QnA, and 28.3% on Terminal-Bench 4.".” ai notis, checked 7 Oct 2026. Source: Mistral Large 4 (Mistral AI). https://ainotis.com/c/662

As a reference (APA style)

ai notis. (2026, October 7). Mistral reports Large 4 scores 61.7% on DeepSWE v1.1, 59.4% on SWE-Atlas-QnA and 28.3% on Terminal-Bench 4. Quote: "scoring 61.7% on DeepSWE v1.1, 59.4% on SWE-Atlas-QnA, and 28.3% on Terminal-Bench 4." [Checked claim 662]. ai notis. https://ainotis.com/c/662

Anyone may quote this address. It does not change; if we correct the story, this page says so.