SWE-bench Verified
Benchmark ● Covered in 14 stories + Follow
SWE-bench Verified 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.
Updated 22 October 2026
Latest developments
2026
Model release: Granite 4.2 & Granite Speech 5.0 Turbo CTC Model release
- Market development: OpenAI & GPT-5.5
- Market development: Recursive Superintelligence & Flint
- Market development: GLM-5.1 & Anthropic
- Market development: JetBrains & Mellum2.1
- Market development: Microsoft Research Asia & Agent Lightning v1.0
- Market development: SCLATE & Qwen3.5-4B
- Market development · 23 Sep 2026
- Market development: OpenAI & Stanford University
- Market development: Microsoft & Agent Lightning v1.0
- Model release: IBM & Granite 4.2
- Market development: Bullet & AppLovin
- Market development: NVIDIA & NOOA
- Market development: NVIDIA & NOOA
- Market development: Microsoft Research & Orchard
Relationships
Products & technology
- Granite 4.2 derived from this benchmark · 1 source
- Agent Lightning v1.0 deploys this benchmark · 1 source
- Mellum2.1 integrated with this benchmark · 1 source
- State of AI Report 2026 derived from this benchmark · 1 source
- SCLATE integrated with this benchmark · 1 source
- Flint integrated with this benchmark · 1 source