RESEARCH Alibaba’s Co-Design Bench Finds Top AI Coding Agent Fully Completes Only 26% of Real Tasks 8/10 2 min read 3 days ago
LAUNCHES Thinking Machines’ Inkling 2 Small Takes the Lead in Western Open-Weight AI 8/10 2 min read 4 days ago
LAUNCHES Google DeepMind Releases Gemini 4 Carbon Just Two Weeks After Argon, Topping the AI Benchmark Charts 8/10 2 min read 2 weeks ago
LAUNCHES Inception’s Mercury 3 Diffusion LLM Claims 1,068 Tokens Per Second 8/10 2 min read 3 weeks ago
TOOL UPDATES Meta Launches Muse Wonder, Claims It Ranks Just Below Claude Opus 5.5 7/10 2 min read 4 weeks ago
BENCHMARKS AI agent teams waste massive tokens for barely measurable quality gains, research finds 8/10 2 min read 1 month ago
LAUNCHES Google Launches Gemini 4 Argon, Claiming the Benchmark Lead With a Cybersecurity Specialty 7/10 2 min read 1 month ago
BENCHMARKS GPT-6 Astra Can Spot Exactly Where You Went Wrong Assembling IKEA Furniture 8/10 2 min read 2 months ago
BENCHMARKS GENSTRAT Benchmark Generates 2,000 Card Games to Test LLM Strategy 7/10 2 min read 6 months ago
BENCHMARKS SOOHAK Benchmark: AI Models Confidently Solve Math Problems That Have No Solution 7/10 3 min read 6 months ago
BENCHMARKS BullshitBench Results Show Anthropic Claude Models Dominate Top Seven Spots in Nonsense Detection Rankings 7/10 4 min read 8 months ago
GUIDES NIST AI 800-3 Introduces Statistical Models to Fix AI Benchmark Gaps 8/10 4 min read 8 months ago
