Checked fact 162116 Oct 2026Models and releases

On the model card's benchmark table Muse Spark Open (xhigh) scores 76.4 on Terminal-Bench 2.1, against 83.9 for GLM 5.3 (max) and 85.0 for Kimi K3 (max).

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

Terminal-Bench 2.1 (Terminus 2 agent) | 76.4 | ... | GLM 5.3 (max) 83.9 | Kimi K3 (max) 85.0

What the source said when we opened it, on 16 Oct 2026.

The source

Muse Spark Open model card
Meta · 2026-10-15

Open the source archived copy

Checked

Checked by the notis newsroom on 16 Oct 2026, against the source above.

The number in it

76.4% · muse-spark-open, benchmark score (Terminal-Bench 2.1 (Meta's model card, xhigh))

In the story

Meta releases open-weight Muse Spark Open under its own licence 16 Oct 2026

Cite this fact

Short permanent address

In a sentence

“On the model card's benchmark table Muse Spark Open (xhigh) scores 76.4 on Terminal-Bench 2.1, against 83.9 for GLM 5.3 (max) and 85.0 for Kimi K3 (max).” ai notis, checked 16 Oct 2026. Source: Muse Spark Open model card (Meta). https://ainotis.com/c/1621

As a reference (APA style)

ai notis. (2026, October 16). On the model card's benchmark table Muse Spark Open (xhigh) scores 76.4 on Terminal-Bench 2.1, against 83.9 for GLM 5.3 (max) and 85.0 for Kimi K3 (max) [Checked claim 1621]. ai notis. https://ainotis.com/c/1621

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