Checked fact 16928 Sep 2026Research

On cumulative full-application reconstruction workflows, GPT-6 Astra achieved 49.2 percent success while Claude Opus 5 reached 28.8 percent.

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

GPT-6 Astra and Claude Opus 5 achieve 49.2% and 28.8% success on cumulative workflows

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

The source

ProgramDistill: benchmarking coding agents on feature discovery in real applications
arXiv · 2026-09-16

Open the source archived copy

Checked

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

The number in it

49.2% · GPT-6 Astra, benchmark score (ProgramDistill cumulative workflows)
28.8% · Claude Opus 5, benchmark score (ProgramDistill cumulative workflows)

In the story

ProgramDistill, a benchmark built from 26 web apps, scores GPT-6 Astra at 49.2 percent and Claude Opus 5 at 28.8. 28 Sep 2026

Cite this fact

Short permanent address

In a sentence

“On cumulative full-application reconstruction workflows, GPT-6 Astra achieved 49.2 percent success while Claude Opus 5 reached 28.8 percent.” ai notis, checked 28 Sep 2026. Source: ProgramDistill: benchmarking coding agents on feature discovery in real applications (arXiv). https://ainotis.com/c/169

As a reference (APA style)

ai notis. (2026, September 28). On cumulative full-application reconstruction workflows, GPT-6 Astra achieved 49.2 percent success while Claude Opus 5 reached 28.8 percent [Checked claim 169]. ai notis. https://ainotis.com/c/169

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