#SWE-Bench

366 related articles

Jul 25, 2026·3 min

Laguna S 2.1: The Open-Source Coding Model That's 14x Smaller Yet Stronger

Poolside releases Laguna S 2.1, an open-source agentic coding model: 118B total params with only 8B active, scoring 40.4% on DeepSWE — ~4.5x DeepSeek V4 Pro Max. Supports 1M-token context, deployable on a single workstation.

Jul 25, 2026·3 min

Kimi K3 Shakes the World: Is Open-Source AI Closing the Gap?

Moonshot AI's 2.8T-parameter open-weight model Kimi K3 rivals Anthropic and OpenAI flagships, sparking a new 'DeepSeek moment' and challenging U.S. AI dominance.

Jul 24, 2026·3 min

OpenAI Releases GPT-5.6 and ChatGPT Work: The Era of Autonomous AI Has Arrived

OpenAI launches GPT-5.6 (Sol, Terra, Luna), ChatGPT Work, a new desktop app, and Sites hosting. AI evolves from a Q&A tool into an autonomous work partner for finance, file management, and more.

Jul 24, 2026·5 min

From Vibe Coding to AI Engineering: A Complete Guide to Enterprise-Grade Development

In the AI programming era, Vibe Coding alone can only build toys. This article deeply analyzes the complete engineering path from Vibe Coding to SDD spec-driven development, covering Claude Code and Codex tool selection, the SuperPower plugin, and domestic LLM comparisons.

Jul 23, 2026·3 min

Vibe Coding for Beginners: Build Your First Project with AI from Scratch

What is Vibe Coding? Learn this new AI programming paradigm from scratch — no CS degree needed. Use Claude Code, Cursor, and more to build real projects by describing your ideas.

Jul 23, 2026·3 min

Grok 4.5 Review: A Full Breakdown of Elon Musk's Most Powerful AI Coding Model

xAI releases Grok 4.5, ranking #1 on SWE Marathon and outperforming Claude Opus. Explore benchmark scores, Agent capabilities, free access, and CLI installation.

Jul 23, 2026·3 min

Claude Code Artifacts Now Open: AI Agent Race Shifts Into High Gear

Claude Code Artifacts opens to Pro/Max users with real-time web deployment. Roundup of AI Agent news: Alipay Abao beta, ByteDance EdgeBench, Microsoft Frontier Company, and OpenAI/Anthropic compute strategies.

Jul 23, 2026·7 min

Qwen3 235B A22B in Practice: A 2.4-Trillion-Parameter Open Model Surpasses Claude Opus

Hands-on with Alibaba Tongyi Qianwen's strongest Qwen3: a 2.4-trillion-parameter open weight model scoring 81.25% on KingBench, ranking second and beating Claude Opus 4.8 with perfect scores in game dev, math, and agent tasks.

Jul 23, 2026·3 min

Claude Sonnet 5 Deep Dive: Impressive Benchmarks, Questionable Value — Just Use Opus 4.8?

Claude Sonnet 5 review: 63.2% SWE-bench, near Opus 4.8 performance, but new tokenizer hides real costs. Ranks 13th on CursorBench. Most tasks: stick with Opus 4.8.

Jul 23, 2026·5 min

Inside Cursor: How Recursive Model Improvement Enables AI to Self-Evolve

A Cursor ML engineer breaks down AI training methodology: outer/inner loop acceleration, preventing reward hacking, textual feedback, and recursive self-improvement (RSI) where models train the next generation.

Jul 22, 2026·6 min

Claude Sonnet 5 In-Depth Testing: 8 Real-World Tasks Reveal Its True Capability Boundaries

Bilibili creator KaterSony tests Claude Sonnet 5 across 8 real-world tasks—image recognition, 3D modeling, web generation—comparing it against GPT-5.5, Gemini 3.1 Pro, and revealing its true capability limits and cost traps.

Jul 22, 2026·3 min

Claude Sonnet 5 Deep Dive: Impressive Benchmarks, Disappointing Reality — Stick with OPUS 4.8

Anthropic's Claude Sonnet 5 claims near-OPUS 4.8 performance at lower cost. Real-world tests reveal hidden tokenizer costs, weak creative output, and only 13th place on Cursor rankings.

Jul 22, 2026·6 min

The Evolution of Claude Code: From Manual Review to 65% Fully-Automated PRs

Anthropic engineers reveal Claude Code's 18-month evolution: system prompt cut by 80%, 65% of PRs shipped automatically by AI, Claude Tag collaboration, and the safety logic behind auto mode.

jcode Deep Dive: Why Rust Is the Ideal…

Jul 22, 2026·3 min

jcode Deep Dive: Why Rust Is the Ideal Foundation for a Coding Agent Framework

jcode is an open-source Coding Agent framework built in Rust, gaining nearly 200 GitHub Stars in a day. Explore its architecture, Rust advantages, and application potential.

Jul 22, 2026·4 min

UK Sovereign AI: How Cosine AI Is Punching Above Its Weight Against American Compute Dominance

Cosine AI founder reveals how the UK's first sovereign LLM is being built — from government compute grants and RL credit attribution to multi-agent orchestration and synthetic data pipelines.

Jul 22, 2026·2 min

Vibe Coding on a Budget: The Brain-vs-Hands Multi-Agent Strategy for Saving Tokens

Always burning through your AI coding quota? This guide breaks down a brain-vs-hands multi-agent strategy: use strong models only for planning, and cheap models like DeepSeek for execution.

Jul 21, 2026·3 min

Ornith 9B/35B Hands-On: A New Local Deployment Option for Code Agents

Ornith 1.0 by Deep Reinforce reinforces Qwen 3.5 for code agents. We test Ornith 9B & 35B MoE on Chinese writing, logic, and invoice OCR, with full llama.cpp deployment guide.

Jul 20, 2026·2 min

Vibe Coding for Beginners: Build Real Apps with AI — No Coding Skills Required

Vibe Coding lets you build real apps using natural language — no coding skills needed. Learn the 3 core traits, see real success stories, and get started today.

Jul 20, 2026·3 min

Zero-Code Xianxia Game Development: A Head-to-Head Comparison of Four Major AI Models

A Bilibili creator built a 2D xianxia game using zero code via Vibe Coding, testing GPT, Claude, Grok, and Doubao with the same 3,000-line prompt. Full workflow breakdown and rankings inside.

Jul 20, 2026·3 min

GPT-5.6 Sol In-Depth Review: Can It Really Challenge Claude Sonnet on Cost Efficiency?

A deep dive into OpenAI GPT-5.6 Sol: benchmark scores rival Claude, coding agent performance leads competitors, yet costs a fraction. But model cheating risks, access limits, and real-world gaps deserve attention.