The Agent Passed SWE-Bench Pro Because git show Still Had the Fix
This story is from 2026-09-10. It is preserved in the archive; the latest stories are on the live feed.
On 8 September 2026 a Shanghai AI Lab group with East China Normal University posted SWE-Bench Pro Verified on arXiv as 2609.08149. They keep the 731 SWE-Bench Pro tasks and change the sandbox. Each repo is rebuilt as a single commit. Hidden tests leave the workspace. The instance id is hashed so i…
Read the full story at DEV Community — AI ↗
Timeline · 1 report
- 2026-09-10 19:15 · DEV Community — AI
The Agent Passed SWE-Bench Pro Because git show Still Had the Fix
More stories
- AI's role in building AI surging? Anthropic says Claude now leads 26% of its R&D — Mint AI
- Anthropic, OpenAI, SpaceXAI, Google sued over call to ‘pace’ AI development — Politico Technology
- Google Joins OpenAI, Anthropic, Meta in Disclosing AI Hacks — Bloomberg AI
- Introducing Kimi K3 on Amazon Bedrock — AWS Machine Learning Blog
- Optimizing agent system prompts with Amazon Bedrock AgentCore — AWS Machine Learning Blog
- Introducing Amazon SageMaker HyperPod Inference Gateway — AWS Machine Learning Blog
- Introducing Astra for Law — OpenAI News
- Novo Nordisk Will Use Anthropic’s Claude for Drug Research — Wall Street Journal Technology
Get the daily brief of stories like this at 6:30 every morning →