Checked fact 21730 Sep 2026Models and releases

Anthropic reports Sonnet 5.5 scores 70.6 percent on Terminal-Bench 4.0, against 10.3 percent for Sonnet 5. Quote: "Sonnet 5.5 scores 70.6% on Terminal-Bench 4.0, an agentic coding evaluation, compared to Sonnet 5"

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

Sonnet 5.5 scores 70.6% on Terminal-Bench 4.0, an agentic coding evaluation, compared to Sonnet 5’s 10.3%.

What the source said when we opened it, on 29 Sep 2026.

The source

Claude Sonnet 5.5
Anthropic · 2026-09-28

Open the source archived copy

Checked

Checked by the notis newsroom on 29 Sep 2026, against the source above.

The number in it

70.6% · Claude Sonnet 5.5, benchmark score (Terminal-Bench 4.0)

In the story

Anthropic releases Claude Sonnet 5.5, which it says is faster than Sonnet 5 30 Sep 2026

Cite this fact

Short permanent address

In a sentence

“Anthropic reports Sonnet 5.5 scores 70.6 percent on Terminal-Bench 4.0, against 10.3 percent for Sonnet 5. Quote: "Sonnet 5.5 scores 70.6% on Terminal-Bench 4.0, an agentic coding evaluation, compared to Sonnet 5".” ai notis, checked 29 Sep 2026. Source: Claude Sonnet 5.5 (Anthropic). https://ainotis.com/c/217

As a reference (APA style)

ai notis. (2026, September 29). Anthropic reports Sonnet 5.5 scores 70.6 percent on Terminal-Bench 4.0, against 10.3 percent for Sonnet 5. Quote: "Sonnet 5.5 scores 70.6% on Terminal-Bench 4.0, an agentic coding evaluation, compared to Sonnet 5" [Checked claim 217]. ai notis. https://ainotis.com/c/217

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