Gemini 2.5 Pro
Google DeepMind's flagship thinking model with 1M-token context, 84% GPQA Diamond, and native multimodal understanding of text, images, audio, and video.
Articles Tagged "Benchmarks"
Suleiman Claims AI Takes White-Collar Jobs in 18 Months
Microsoft AI CEO Mustafa Suleiman says professional jobs face automation within 18 months. The data from independent studies tells a different story.
Self-Correcting Models, Smarter Monitors, AI Designs Itself
Three new papers tackle critique dependency in LLMs, ensemble monitoring for AI control, and agents that autonomously discover better neural architectures.
Claude Opus 4.5
Anthropic's November 2025 flagship model delivers top SWE-bench scores, a new effort parameter for reasoning control, and a 66% price cut from its predecessor.
Open Agent Leaderboard: Model Beats Architecture
IBM Research tests 25 agent configurations across 6 real-world benchmarks and finds backbone model choice matters 58x more than agent framework design.
Thinking Machines Builds AI That Listens While Talking
Mira Murati's startup unveils TML-Interaction-Small, a 276B MoE model that hits 0.40-second response latency by listening and generating speech at the same time.
IBM Granite Embedding R2 Brings 32K Context to Search
IBM's Granite Embedding Multilingual R2 ships with a 64x context window jump, ModernBERT architecture, and Apache 2.0 licensing that makes it enterprise-safe out of the box.
Physics Predicts AI Risk, Math Still Hard, Tokens Saved
A physics formula predicts AI behavioral shifts before they happen, a benchmark shows LLMs fail at 90% of graduate math formalization, and a training-free method cuts synthetic data costs by up to 78%.
SubQ Review: 52x Faster, but Show Your Work
Subquadratic's SubQ claims the first linear-scaling LLM with a 12M-token window - but private beta access, self-reported benchmarks, and a 17-point MRCR gap make independent verification the only test that matters.
GAIA Benchmark Leaderboard: Best AI Agents May 2026
Rankings of the best AI models and agent frameworks on the GAIA benchmark, which tests real-world multi-step tasks requiring web browsing, tool use, and multi-hop reasoning.
Claude Haiku 4.5
Anthropic's fastest and most cost-efficient model, delivering 73.3% on SWE-bench Verified and first-in-family extended thinking and computer use at $1/$5 per million tokens.
GPT-4.1
OpenAI's coding-optimized API model with a 1M token context window, 54.6% SWE-bench Verified score, and $2/$8 per million token pricing.
