Tagged articles

AI model benchmark

6 articles · Page 1 of 1

Aug 4, 2026 · Industry Insights

Qwen3.8-Max Secures Fourth Place on Frontend Code Arena Leaderboard

Alibaba's Tongyi Qianwen team announced that the flagship model Qwen3.8‑Max achieved a score of 1,668 to rank fourth on the Frontend Code Arena benchmark, trailing Claude Opus 5 (High) by just one point and staying within 37 points of the top‑scoring Claude Opus 5 (Max), while also earning strong placements across multiple sub‑domains such as Consumer Product (#2) and Gaming (#3).

AI model benchmarkClaude OpusFrontend Code Arena

0 likes · 3 min read

Qwen3.8-Max Secures Fourth Place on Frontend Code Arena Leaderboard

AI Engineering

Jul 1, 2026 · Artificial Intelligence

Claude Sonnet 5 Is Stronger Yet Costlier—Per‑Task Cost Beats Opus 4.8

Anthropic’s newly released Claude Sonnet 5 scores 53 on the Artificial Analysis intelligence index, surpassing Sonnet 4.6 and matching GPT‑5.5, but its per‑task cost rises to $2.29—15 % higher than Opus 4.8—due to roughly 40 % more output tokens and increased agentic interaction rounds.

AI model benchmarkAgentic AIAnthropic

0 likes · 5 min read

Claude Sonnet 5 Is Stronger Yet Costlier—Per‑Task Cost Beats Opus 4.8

Architect's Guide

May 29, 2026 · Artificial Intelligence

What Makes DeepSeek V4 Different? A Deep Technical Dive into Its Innovations

DeepSeek V4 introduces a suite of architectural breakthroughs—including mixed‑expert MoE, manifold‑constrained hyper‑connections, CSA/HCA hybrid attention, and FP4 quantization—that slash inference cost by up to tenfold while delivering million‑token context, competitive benchmarks, dual model variants, and a disruptive pricing strategy.

AI model benchmarkAgentic AIDeepSeek-V4

0 likes · 41 min read

What Makes DeepSeek V4 Different? A Deep Technical Dive into Its Innovations

DataFunTalk

Apr 25, 2026 · Artificial Intelligence

DeepSeek‑V4 vs GPT‑5.5: First Real‑World Tests Reveal Surprising Results

On the day GPT‑5.5 launched, DeepSeek‑V4 followed, and a series of head‑to‑head tests—including a logic puzzle, an IMO math problem, HTML generation, game‑engine coding, token‑efficiency measurement, and a network‑security challenge—showed GPT‑5.5 generally leading while DeepSeek demonstrated notable strengths and cost advantages.

AI model benchmarkAI securityDeepSeek-V4

0 likes · 14 min read

DeepSeek‑V4 vs GPT‑5.5: First Real‑World Tests Reveal Surprising Results

Programmer's Advance

Jan 21, 2026 · Artificial Intelligence

Why GLM‑4.7‑Flash Delivers 70B‑Level Performance with Only 30B Parameters

GLM‑4.7‑Flash, released by Zhipu AI on Jan 20 2026, uses a Mixture‑of‑Experts (MoE) backbone and a Multi‑Latent Attention (MLA) mechanism to achieve near‑70B model quality with just 30 B total and 3 B active parameters, running on a single 24 GB GPU or even a Mac, while remaining fully open‑source and free to use.

AI model benchmarkGLM-4.7-FlashMixture of Experts

0 likes · 15 min read

Why GLM‑4.7‑Flash Delivers 70B‑Level Performance with Only 30B Parameters

AI Insight Log

Dec 23, 2025 · Artificial Intelligence

GLM-4.7 Beats GPT-5 in Coding Tests at One‑Seventh the Cost

Zhipu's newly released GLM-4.7 model outperforms GPT-5 and Claude Sonnet 4.5 on multiple coding benchmarks, introduces Vibe Coding for UI generation, offers Interleaved and Preserved Thinking capabilities, is fully open‑source, and costs only one‑seventh of competing services.

AI model benchmarkGLM-4.7code generation

0 likes · 6 min read

GLM-4.7 Beats GPT-5 in Coding Tests at One‑Seventh the Cost