<description>&lt;p&gt;&lt;br&gt;&lt;/p&gt;&lt;p&gt;&lt;br&gt;&lt;/p&gt;&lt;p&gt;Avengers-Pro is a test-time routing framework that optimizes performance and efficiency in LLMs, achieving state-of-the-art results by dynamically assigning queries to suitable models based on performance-efficiency scores.&lt;/p&gt;&lt;p&gt;&lt;br&gt;&lt;/p&gt;&lt;p&gt;https://arxiv.org/abs//2508.12631&lt;/p&gt;&lt;p&gt;&lt;br&gt;&lt;/p&gt;&lt;p&gt;YouTube: https://www.youtube.com/@ArxivPapers&lt;/p&gt;&lt;p&gt;&lt;br&gt;&lt;/p&gt;&lt;p&gt;TikTok: https://www.tiktok.com/@arxiv_papers&lt;/p&gt;&lt;p&gt;&lt;br&gt;&lt;/p&gt;&lt;p&gt;Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016&lt;/p&gt;&lt;p&gt;&lt;br&gt;&lt;/p&gt;&lt;p&gt;Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers&lt;/p&gt;&lt;p&gt;&lt;br&gt;&lt;/p&gt;
</description>

Avengers-Pro is a test-time routing framework that optimizes performance and efficiency in LLMs, achieving state-of-the-art results by dynamically assigning queries to suitable models based on performance-efficiency scores. https://arxiv.org/abs//2508.12631 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016 Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers

Arxiv Papers

Beyond GPT-5: Making LLMs Cheaper and Better via Performance–Efficiency Optimized Routing

Beyond GPT-5: Making LLMs Cheaper and Better via Performance–Efficiency Optimized Routing

Description