So it's trained on the SWE Bench Pro evalset
That's not accurate. Take a look at the paper to see what it is trained on! And specifically decontamination is called out in A.4
https://microsoft.ai/wp-content/uploads/2026/06/main_2026060...
What is your evidence for this claim?
alt Hacker News
That's not accurate. Take a look at the paper to see what it is trained on! And specifically decontamination is called out in A.4
https://microsoft.ai/wp-content/uploads/2026/06/main_2026060...