Randomly switching between LMs at every step boosts SWE-bench score

Show HN: Randomly switching between LMs at every step boosts SWE-bench score

Randomly switching between LMs at every step boosts SWE-bench score is a company in show hn launch.

Profile

What if your agent uses a different LM at every turn? We let mini-SWE-agent randomly switch between GPT-5 and Sonnet 4 and it scored higher on SWE-bench than with either model separately.GPT-5 by itself gets 65.0%, Sonnet 4 64.8%, but randomly switching at every step gets us 67.2%This result came pretty surprising to us. There's a few more experiments in the blog post.

As a business in show hn launch, Randomly switching between LMs at every step boosts SWE-bench score is listed here with the public details available about it.

Its current recorded stage is Show HN launch.

Website: www.swebench.com/SWE-bench/blog/2025/08/19/mini-roulette