Technology ❯ Artificial Intelligence

Benchmarking

Performance Metrics Performance Evaluation Performance Comparison Model Performance Performance Testing AI Performance Metrics Evaluation Metrics ARC-AGI Model Evaluation LMArena

Alibaba Launches Qwen 3.6 Max-Preview, Its Most Powerful AI Model

The move signals a turn to a paid, hosted flagship for enterprise AI.

Alibaba Confirms HappyHorse AI Video Model Leading Blind Benchmarks

Nvidia Launches Nemotron 3 Super, an Open 120B Model for Agentic, Long‑Context AI

Google Releases Gemini 3.1 Pro in Preview With Major Reasoning Gains

OpenAI Begins Phased Rollout of GPT-5.2 in Three Variants to Paid Users

Nvidia Claims 10x MoE Inference Gains With New 72‑Chip AI Server

xAI Rolls Out Grok 4.1 Free to All Users, Citing Faster, More Accurate Replies

Anthropic Launches Claude Sonnet 4.5 With Claims of Production-Ready Coding

Samsung Unveils TRUEBench to Measure LLM Productivity in Real-World Tasks

ByteDance Launches Seedream 4.0 to Challenge Google DeepMind’s ‘Nano Banana’

Google Unveils Gemini 2.5 Pro Preview and Doubles Pro Subscription Queries

LM Arena Defends Chatbot Arena Benchmark Amid Transparency Concerns

Alibaba Unveils Qwen2.5-Omni-7B AI Model for Multimodal Use on Everyday Devices

SoundHound AI Surges After Q4 Earnings Beat and Raised 2025 Revenue Outlook

OpenAI's o3 Model Achieves Human-Level Performance on Key Intelligence Test

Microsoft Unveils Phi-4, a Small AI Model Excelling in Complex Reasoning

Anthropic Releases Claude 3.5 Haiku AI Model to All Users

Meta Releases Llama 3.3, a Smaller, Cost-Efficient AI Model That Matches Top Competitors

Geekbench AI 1.0 Launches to Measure Cross-Platform AI Performance

Black Forest Labs Unveils FLUX.1, Redefining Text-to-Image AI