Checked fact 19828 Sep 2026Models and releases

In Fireworks own comparison against Kimi K3 at max effort, Ember-1 shows reductions of 51.9 percent on Terminal Bench 2.1, 23.7 percent on DeepSWE 1.1 and 15.5 percent on SWE-bench Verified.

Toned down to what the source says

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

Ember-1 vs. K3 Max: Terminal Bench 2.1 -51.9% / -23.1 USD; SWE-bench Verified -15.5% / -68.1 USD; DeepSWE 1.1 -23.7% / -126.9 USD

What the source said when we opened it, on 28 Sep 2026.

The source

Introducing Ember-1
Fireworks AI · 2026-09-23

Open the source archived copy

Checked

Checked by the notis newsroom on 28 Sep 2026, against the source above.

In the story

Fireworks says its Ember-1 research preview delivers Kimi K3 quality with 40 percent fewer tokens. 28 Sep 2026

Cite this fact

Short permanent address

In a sentence

“In Fireworks own comparison against Kimi K3 at max effort, Ember-1 shows reductions of 51.9 percent on Terminal Bench 2.1, 23.7 percent on DeepSWE 1.1 and 15.5 percent on SWE-bench Verified.” ai notis, checked 28 Sep 2026. Source: Introducing Ember-1 (Fireworks AI). https://ainotis.com/c/198

As a reference (APA style)

ai notis. (2026, September 28). In Fireworks own comparison against Kimi K3 at max effort, Ember-1 shows reductions of 51.9 percent on Terminal Bench 2.1, 23.7 percent on DeepSWE 1.1 and 15.5 percent on SWE-bench Verified [Checked claim 198]. ai notis. https://ainotis.com/c/198

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