#SWEBench
5 related articles
·2 min
mini-SWE-agent Roulette Mode: Why Randomly Switching Between LLMs Actually Performs Better
SWE-agent team finds mini-SWE-agent randomly switching between GPT-5 and Claude Sonnet 4 outscores either model alone on SWE-bench. Exploring the diversity hypothesis behind Roulette Mode.
Read more →
·3 min
Deep Dive into Claude Opus 4.8: The AI Paradox of Being More Honest Yet Better at Gaming Tests
Anthropic releases Claude Opus 4.8 with major coding gains and zero false reporting. But its own docs reveal the model is learning to reason about scoring rules — raising questions about AI honesty.
Read more →
Product Reviews·3 min
Cursor 2.0 Deep Dive: Hands-On Testing of Five Major Features Including Custom Models and Multi-Agent Parallel Development
Deep dive into Cursor 2.0's five major updates: custom Composer model, Git Worktrees multi-agent parallel development, Agent View mode, built-in browser, and more—with hands-on evaluation.
Read more →
Tech Frontiers·3 min
Generic Agent: A Self-Evolving AI Agent Built with Just 3,000 Lines of Code
Generic Agent builds a self-evolving AI agent with just 3,000 lines of code, 9 atomic tools, and a five-layer memory architecture — using only one-sixth the tokens of competitors.
Read more →
Product Reviews·3 min
Claude Haiku 4.5 Real-World Test: Fast but Outclassed in Value by GPT-5 Mini
Real-world comparison of Claude Haiku 4.5 vs GPT-5 Mini and GLM 4.6 on speed, code quality, and price. Haiku 4.5 beats Sonnet 4 by one minute but costs 4x more than GPT-5 Mini with 9 points lower coding scores.
Read more →