Checked fact 316330 Oct 2026Models and releases

Mistral says Large 4 scores 48% on the Artificial Analysis Coding Agent Index, effectively tied with GLM-5.3, using 47% fewer tokens per task on average.

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

On the Artificial Analysis Coding Agent Index, Mistral Large 4 scores 48%, effectively tied with the leading open-weight model, GLM-5.3, while using 47% fewer tokens per task on average.

What the source said when we opened it, on 30 Oct 2026.

The source

Mistral Large 4 weights
Mistral AI · 2026-10-29

Open the source archived copy

Checked

Checked by the notis newsroom on 30 Oct 2026, against the source above.

The number in it

48% · Mistral Large 4, benchmark score (Artificial Analysis Coding Agent Index)

In the story

Mistral releases Large 4 weights, but paid hosting needs a separate licence 30 Oct 2026

Cite this fact

Short permanent address

In a sentence

“Mistral says Large 4 scores 48% on the Artificial Analysis Coding Agent Index, effectively tied with GLM-5.3, using 47% fewer tokens per task on average.” ai notis, checked 30 Oct 2026. Source: Mistral Large 4 weights (Mistral AI). https://ainotis.com/c/3163

As a reference (APA style)

ai notis. (2026, October 30). Mistral says Large 4 scores 48% on the Artificial Analysis Coding Agent Index, effectively tied with GLM-5.3, using 47% fewer tokens per task on average [Checked claim 3163]. ai notis. https://ainotis.com/c/3163

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