2/5 isn't quality, it's consistency as written there. The full links are at the bottom. Most of Spark's attempts are failures:

https://d1md4c6gq9re9p.cloudfront.net/blog/gpt-5.6-buildoff/...

https://d1md4c6gq9re9p.cloudfront.net/blog/gpt-5.6-buildoff/...

https://d1md4c6gq9re9p.cloudfront.net/blog/gpt-5.6-buildoff/...