AI Briefing#swe-2-flash
The latest AI and developer news about #swe-2-flash, with the original source and a short summary.
The latest AI and developer news about #swe-2-flash, with the original source and a short summary.
The 276B-A12B model achieves 20.0% on Terminal-Bench 4.0 and 24.0% on FrontierCode 2.0, running at 200 tokens per second.