News for hackers. Stuff that matters.

A comment on Ornith-1.5: From Self-Scaffolding to Self-Improvement.

Re:Ornith-1.5: From Self-Scaffolding to Self-Improvement by lsb on Wednesday August 19, 2026 @05:21PM (#49367372)
The page has comparisons with Qwen 3.6 27b and I’d love to see comparisons with Qwen 3.8 27b, the newer one is much more capable!
[ Parent | on HN ]
Re:Ornith-1.5: From Self-Scaffolding to Self-Improvement by ricardobeat on Wednesday August 19, 2026 @06:21PM (#49367938)
It's somewhat close, but a lot worse at code it seems. Qwen 3.8 is a wild improvement over 3.6.

                               Qwen 3.8-27B     Ornith-1.5-35B
    
    Terminal-Bench 2.1         73.0             67.8
    SWE-bench Pro              61.7             59.6
    DeepSWE (1.1)              42.2             22.0
    NL2Repo                    42.3             46.2
    GPQA Diamond               89.2             89.2
    Humanity's Last Exam       30.8             25.6
[ Parent | on HN ]