Видео с ютуба Swe-Bench

Evaluate agents on SWE-Bench

Interpreting SWE-bench Scores

SWE-Bench authors reflect on the state of LLM agents at Neurips 2024

John Yang - SWE-bench: Can Language Models Resolve Real-World GitHub Issues?

SWE bench & SWE agent | Data Brew | Episode 44

AI Agent Automatically Codes WITH TOOLS - SWE-Agent Tutorial ("Devin Clone")

What do AI Benchmarks Actually Mean?! A Fast Breakdown (MMLU, SWE-bench, & More Explained)

Computer Science FAILURE to $500k SWE

Claude 4.1 DESTROYED GPT-5 in Coding! 74.5% on SWE-bench - IS THIS THE END OF OpenAI?

Goast.AI fixes an error on FIRST TRY from the SWE-Bench dataset used by Devin

The #1 SWE-Bench Verified Agent

Multi-SWE-bench: Testing LLMs on Real-World Code Issues

SWE-Agent: The New Open Source Software Engineering Agent Takes on DEVIN

princeton-nlp/SWE-bench - Gource visualisation

[Paper Club] SWE-Bench [OpenAI Verified/Multimodal] + MLE-Bench with Jesse Hu

Build SWE Agent using @LlamaIndex | Software Engineer AI Agent | SWE Bench

Claude Opus 4.1: 74.5% en SWE-bench — récord de programación.

BLACKBOXAI tops swe-bench #cline #aider #windsurf #cursor #vscode #swebench #aicoding

Скандал з оцінками моделей у SWE bench 😳