2h ago

Composer 2.5 Ranks #5 on FrontierSWE, Matches Gemini 3.1 Pro

0
Original post

Composer 2.5 is ranked #5 on FrontierSWE The model is broadly on par with Gemini 3.1 Pro, with a slight edge in our evaluation, and it beats all open source models. We still observe a significant performance gap between Composer and models from Anthropic and OpenAI

2:20 PM · May 26, 2026 View on X
Composer 2.5 Ranks #5 on FrontierSWE, Matches Gemini 3.1 Pro · Digg