Models
Qwen3.5-35B-A3B
An open-weight language model used in LEASH experiments to demonstrate cost-efficient weak-to-strong escalation.
0 stories.
Every story about Qwen3.5-35B-A3B (0)
No story is about Qwen3.5-35B-A3B yet: the ones below only mention it.
Also mentioned in (1)
Stories about something else that name Qwen3.5-35B-A3B in passing, with the sentence that does.
- LEASH helps AI agents know when to ask for help“With Qwen3.5-35B-A3B, LEASH reached 73.66 percent task success at about $0.41 per task, while always-running Claude Opus 5 scored 72.90 percent at higher cost.”