Understand this story
On October 28, 2026, Dex Horthy posted the latest Slopcode Bench evaluation results on X, along with a link to episode 79 of "AI That Works." A retest article published the same day shows that the author retested frontier models using the full version of SlopCodeBench (36 problems, 196 checkpoints per setting); the highest was GPT-6 Astra with a strict pass rate of 16.3%, higher than GPT-5.5's 14.8% in May, and the participating models overall fell between 12.2% and 16.3%. In the three full comparisons, the XHigh tier cost 2.11-4.22 times that of Medium, but Opus 5.5 actually had more strict passes in the Medium tier (28 versus 25), while Astra and SOL performed better in the XHigh tier. Regarding code quality, Opus 5.5 XHigh's slop line proportion was 77.75%, lower than Medium's 94.25%; the author cautions that this may be because the new models produce new anti-patterns not yet covered by the more than 200 linters.
AI-generated from public reports
Latest development · Report
Dex Horthy announces new Slopcode Bench resultsDevelopments
1 confirmed developments
- Source:Dex Horthy
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Oct 28
Dex Horthy
Dex Horthy announces new Slopcode Bench results
Dex Horthy posted the latest Slopcode Bench evaluation results on X, along with a link to episode 79 of "AI That Works."
Dex Horthy
SlopCodeBench Retest: GPT-6 Astra Leads with 16.3% Strict Pass Rate, Ahead of Opus 5.5
The author retested frontier models using the full version of SlopCodeBench (36 questions, 196 checkpoints per setting). The highest was GPT-6 Astra with a strict pass rate of 16.3%, above GPT-5.5's 14.8% in May, with the tested models overall ranging from 12.2% to 16.3%. In the three full comparisons, the XHigh tier cost 2.11-4.22 times that of Medium, but Opus 5.5 actually had more strict passes at the Medium tier (28 vs. 25), while Astra and SOL performed better at the XHigh tier. Regarding code quality, Opus 5.5 XHigh had a slop line proportion of 77.75%, lower than Medium's 94.25%; the author cautions that this may be because the new models produce new anti-patterns not yet covered by the 200-plus linters.