← Back to Home

#long-context

2 entries with this tag

🔬 research2026-06-18T00:00:00.000Z

GLM-5.2: Zhipu AI's 1M-Context Open Frontier Model — Long-Horizon Coding, IndexShare Architecture, and the Open-Source Challenge to the Closed-Weight Elite

Zhipu AI releases GLM-5.2 on June 16, 2026 — a 744B MoE model with solid 1M-token context, MIT license, and long-horizon coding capability that trails Claude Opus 4.8 by only 1% on FrontierSWE. Analyzes the IndexShare architecture, speculative decoding improvements, agentic RL training, and positions GLM-5.2 against the closed-weight frontier (Fable 5, Opus 4.8, GPT-5.5, Qwen3.7 Max).

#GLM#Zhipu AI#Open-Source#Long-Context#Agentic Coding
🔬 research2026-04-24T00:00:00.000Z

DeepSeek-V4-Pro: Efficient Million-Token Context with Hybrid Attention and MoE Architecture (April 2026)

Analysis of DeepSeek-V4-Pro (1.6T params, 49B activated) and DeepSeek-V4-Flash (284B params, 13B activated) featuring hybrid attention architecture (CSA+HCA), 1M-token context, and three reasoning modes. Comprehensive comparison with frontier models (K2.5, M2.7, GLM-5.1, Qwen3.5-27B, Gemma 4 31B) across reasoning, coding, agentic tasks, and long-context domains.

#ai#models#deepseek#efficient#mixture-of-experts#long-context#reasoning#comparison