#Frontier Code benchmark

403 related articles

Jul 25, 2026·2 min

Three Chinese LLMs Launch in Parallel: Qwen, DeepSeek V4, and GLM Next-Gen Models Arriving Soon

Alibaba's next-gen Qwen, DeepSeek V4 GA, and Zhipu's new GLM are all nearing release. Explore the latest progress, hands-on results, and distillation controversy of China's top LLMs.

Jul 25, 2026·3 min

Anthropic's Hands-On Guide: How to Scientifically Choose and Evaluate AI Models

Anthropic's Applied AI team breaks down a methodology for choosing AI models: building custom evals, avoiding three common pitfalls, measuring value by cost per success, and cutting costs with prompt caching and context engineering.

Jul 25, 2026·1 min

Grok 4.5 Free in Cursor: Performance, Cost, and Usage Guide

xAI's Grok 4.5 has landed in the Cursor editor, free on all plans. This guide covers how to enable it, benchmark performance, token cost comparisons, and practical mix-and-match strategies to maximize this free window.

Jul 25, 2026·5 min

DeepSeek's Five-Step Ladder to AGI: A Restrained Roadmap Built on Twenty Thousand GPUs

DeepSeek founder Liang Wenfeng reveals a five-step AGI roadmap from chain-of-thought to embodied intelligence. How does TileLang crack domestic GPU substitution under a 20,000-card constraint?

Jul 25, 2026·5 min

DeepSeek's Five-Step Ladder to AGI: A Restrained Roadmap Built on 20,000 GPUs

DeepSeek founder Liang Wenfeng reveals a five-step AGI roadmap—from chain-of-thought to embodied intelligence—under a 20,000-GPU constraint, using the TileLang compiler to break domestic substitution challenges while API cash flow backs AGI exploration.

Jul 25, 2026·3 min

Rocky: An Open-Source Coding Agent with Minimal Architecture and Native DeepSeek Integration

Rocky is a minimal, transparent open-source coding agent with a core loop under a few hundred lines of Python, native DeepSeek search, Research mode, and built-in SWE benchmarking for reproducible agent experiments.

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

DeepSeek Open-Sources DeepSpec: A Full-Stack Speculative Decoding Library with 60–85% Inference Speedup

DeepSeek open-sources DeepSpec, a full-stack speculative decoding library delivering 60–85% inference speedup and up to 661% throughput gains in production. MIT license, 9 checkpoints, 9 benchmarks.

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, 2026·8 min

A Complete Guide to Agent Testing: Five Core Dimensions and Automation in Practice

In-depth analysis of the five core dimensions of AI Agent testing: command safety, tool-calling accuracy, task planning, output consistency, and error self-repair. Master automated testing and the transition path for test engineers.

Jul 24, 2026·8 min

The Complete Guide to Agent Testing: Five Core Dimensions and Automation in Practice

An in-depth analysis of the five core dimensions of AI Agent testing: command safety, tool-calling accuracy, task planning, output consistency, and error self-repair. Master automated testing methods and the transition path for test engineers.

Jul 24, 2026·6 min

Making Money with AI Coding Gigs: A Sober Breakdown and Honest Assessment of the Four-Week Learning Path

Can beginners really earn over 10,000 yuan in their first month with AI coding gigs? This article breaks down the four-week AI coding learning path week by week and objectively assesses the real monetization barriers.

Jul 24, 2026·7 min

DeepSeek's Mysteriously Retracted Paper: Breaking AI's Multimodal Reasoning Bottleneck with Visual Primitives

DeepSeek's paper 'Thinking with Visual Primitives' was online for just 4 hours before being pulled. It uses bounding boxes and points as reasoning primitives, letting models 'point at' images to outperform GPT, Gemini, and Claude on maze navigation and counting.

Jul 23, 2026·3 min

Codex Beginner's Guide: A Step-by-Step AI Work Assistant Tutorial for Non-Coders

Complete beginner's guide to OpenAI Codex desktop client: installation, setup, project management, and plugins — no coding required. Let AI actually do work for you.

Jul 23, 2026·3 min

OpenAI Bets $600K on Rust: Why AI Giants Are Collectively Pivoting to Systems Programming

OpenAI joins the Rust Foundation as a Platinum Member with $600K. xAI and Anthropic are also building Rust infrastructure. Here's why AI giants are betting big on Rust.

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, 2026·3 min

Qwen3.8 Deep Dive: How Does a 2.4 Trillion Parameter MoE Model Claim Second Place?

Alibaba's Qwen3.8 challenges larger models with a 2.4T-parameter MoE architecture, claiming second only to Gemini. A deep dive into MoE mechanics, continuous updates, two-speed release strategy, and real local deployment requirements.

Jul 23, 2026·6 min

Hands-On with Qwen 3.8 Max: How an Open-Source Model Closes In on Top-Tier Closed Models

Qwen 3.8 Max has 2.4 trillion parameters and will be open-sourced. In KingBench testing it scored 81.25%, ranking second, beating Claude Opus 4.8 and trailing only Fable 5. A deep dive into its performance across 8 tests.

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.