Technology ❯ Artificial Intelligence

Performance Evaluation

Benchmarking Benchmarks Model Comparison Benchmark Testing Experimental Results Testing Methods Comparative Analysis Testing Model Limitations Empirical Studies

Sakana Launches Fugu Orchestrator to Coordinate Multiple LLM Agents

The system routes queries through a swappable pool of specialist models to reduce vendor lock-in and preserve high performance.

Nvidia’s ENPIRE Lets AI Coding Agents Teach Robot Fleets Real-World Dexterous Tasks

Google Begins Rollout of Gemini 3.1 Pro, Its Upgraded Core AI Model

Google Rolls Out Gemini 3 Flash as Default in Gemini App, Begins Search AI Mode Deployment

OpenAI Launches GPT-5.2, Rolling Out to Paid ChatGPT Plans in Three Modes

DeepSeek Releases V3.2 Models to Challenge GPT‑5 and Gemini 3 Pro

China Overtakes U.S. in Open-Source AI Downloads

Google Rolls Out Gemini 3 Across Search With New Agents and Paid ‘Deep Think’

Moonshot AI Releases Open-Source Kimi K2 Thinking, a Tool-Using 'Thinking Agent'

Anthropic’s Claude Sonnet 4.5 Often Spots Its Own Tests, Raising Evaluation Questions

DeepSeek Releases Open-Source V3.2‑Exp With Sparse Attention, Cuts API Prices as Huawei Offers 0‑Day Support

Meta Releases Open-Weights Code World Model With Built-In Execution Simulation

New HANRAG Preprint Targets Multi‑hop Noise as RAG Guides Proliferate

Alibaba Debuts Trillion-Parameter Qwen-3-Max-Preview on Cloud and OpenRouter

Google Launches Gemma 3 270M to Enable Hyper-Efficient On-Device AI

Studies Unveil Scaling Laws and Edge Quantization for Mixture-of-Experts Language Models

Z.ai Unveils Open-Source GLM-4.5 Models That Undercut DeepSeek

Alibaba Elevates Qwen3 Open-Source AI with Benchmark-Topping Upgrades

Microsoft Unveils Phi-4 Reasoning Models That Outperform Larger AI Systems

OpenAI Expands GPT-4.5 Access to ChatGPT Plus Users