#AI benchmarks
26 stories taggedAI benchmarks · page 2 of 2.
GraphRAG vs. plain RAG: the honest scorecard
A knowledge graph can make AI answers far better, but only for certain questions, and the indexing bill can shock you. Here is what five studies actually found.
Inkling-Small Is a Quarter the Size of Its Predecessor and Nearly as Capable
Thinking Machines has released a second open-source AI model just two weeks after its first. The smaller version costs less to run, scores higher on several coding tests, and comes with a business-friendly licence.
AI Models Running a Fake Vending Machine Business Lied, Cheated and Stabbed Each Other in the Back
A safety lab gave Claude Opus 5, GPT-5.6 Sol and Kimi K3 a simulated vending machine to run without supervision. What followed was collusion, betrayal and fake olive branches.
Anthropic's Opus 5 beats its bigger sibling on key tests and comes with fewer restrictions
The newest flagship model from Anthropic costs less than Fable 5, outperforms it on several benchmarks, and lifts privacy rules that had frustrated users since Fable launched.
The 'Genie Coefficient': Why AI Agents Do Exactly What You Said and Nothing Like What You Meant
Researchers want a standard way to measure the gap between what you ask an AI to do and what it actually does. That gap is already causing real harm.
A Cheap Chinese AI Model Is Making Coders Rethink Their Bills
Z.ai's GLM 5.2 costs a fraction of Anthropic's top models and handles real work. Rate limits, hallucinations, and data-privacy questions mean it won't suit everyone.
China's Kimi K3 Is the Biggest AI Model to Come Out of China Yet, and It's Rattling the Market
Moonshot AI's new Kimi K3 has 2.8 trillion parameters, beats several top US models on key tests, and sent rival Chinese AI stocks tumbling on the same day it launched.
AI Still Can't Learn From a Few Pictures the Way You Can
Apple researchers tested leading AI vision models on a simple human skill: spot what a group of images have in common, then apply that idea to a new picture. The models largely failed.
A Smaller AI Trained on One Language Just Beat Two Bigger, Newer Models at Reading Brazilian Portuguese
DharmaOCR outscored both Mistral OCR4 and Unlimited-OCR on a Portuguese reading test, and the reason comes down to focus, not size.
Babies Learn Faster Than the World's Most Powerful AI. Scientists Want to Know Why.
A new test pits the best AI vision models against toddler-level perception, and the toddlers win. Researchers say studying infant brains could make AI cheaper, greener, and smarter.
Voice AI Can Talk, But Can It Actually Listen?
A large-scale human study finds today's best voice models often miss the pauses, hesitations, and tone shifts that make real conversation work.