SWE-bench

8 posts · 4 sources

Fireworks AIBlog26 Aug

DeepSeek V4 Pro: Tops SWE-Bench & Cuts Cost per Task by 3x vs. Fable 5

Together AIBlog25 Feb

CoderForge-Preview: SOTA open dataset for training efficient coding agents

Mistral AIBlog9 Dec

Introducing: Devstral 2 and Mistral Vibe CLI.

Together AIBlog25 Jul

Qwen3-Coder: The Most Capable Agentic Coding Model Now Available on Together AI

Together AIBlog2 Jul

DeepSWE: Training a Fully Open-sourced, State-of-the-Art Coding Agent by Scaling RL

Mistral AIBlog21 May

Devstral

AnthropicBlog6 Jan

Claude SWE-Bench Performance

AnthropicBlog6 Jan

Claude SWE-Bench Performance