SWE-bench

Benchmark ● Covered in 8 stories + Follow

SWE-bench is tracked in TLDRocket’s benchmark dataset. Explore the recorded developments, relationships and supporting evidence below. Coverage reflects our monitored sources and may be incomplete.

Latest developments

Market development: Microsoft Research & UC Berkeley MarkTechPost · 1 week ago · 0 Model release: Anthropic & OpenAI Deep Learning Weekly · 1 week ago · 0 Market development: OpenAI & GPT-5.5 Fortune · 0 Market development: Sakana AI & University of British Columbia Exponential View · 2 weeks ago · 0 Product launch: Runway & Solaris YouTube · 3 weeks ago · 0 Research publication: Sakana TheSequence · 1 month ago · 1 Open source release: Meta & Muse Glimmer Simon Willison’s Weblog · 3 months ago · 5 Model release: Alibaba & Qwen 3.8 Max Latent Space · 3 months ago · 6

Timeline

Month Quarter Year

2026

Model release: Anthropic & DeepSeek Model release

Product launch: GWM Worlds 2 & Runway Product launch

Research publication: Google Research & Sakana Research publication

Open source release: Meta & Meta Platforms Inc. Open source release

Model release: Alibaba & Qwen 3.8 Max Model release

30 Oct Market development: Microsoft Research & UC Berkeley
30 Oct Model release: Anthropic & OpenAI
29 Oct Market development: OpenAI & GPT-5.5
26 Oct Market development: Sakana AI & University of British Columbia
14 Oct Product launch: Runway & Solaris
6 Oct Research publication: Sakana
10 Aug Open source release: Meta & Muse Glimmer
4 Aug Model release: Alibaba & Qwen 3.8 Max

Relationships

Products & technology

Sakana AI integrated with this benchmark · 1 source