SubQ
SubQ is the first LLM built on a fully subquadratic attention architecture, achieving a 12M-token research context and 52x faster inference than FlashAttention at 1M tokens.
Articles Tagged "Benchmarks"
Reasoning Bias, Behavior Cues, and Tool Interpretability
New research shows reasoning length amplifies position bias, behavior cues cut wasted tokens by 50% while boosting safety, and sparse autoencoders can predict tool failures from model internals.
Reasoning Model API Pricing Compared - May 2026
Updated May 2026: DeepSeek V4-Flash reasoning now $0.28/MTok output (8x cheaper than R1), o3-pro launched at $20/$80, Grok 4 retires May 15 - verified pricing across 11 models.
NVIDIA Ising Review: AI Models for Quantum Hardware
NVIDIA Ising is the first open AI model family for quantum computing - a 35B VLM for processor calibration and CNN decoders for real-time error correction, already deployed at 20+ research institutions.
AI2 Fires Up $152M Blackwell Cluster for Open Science
AI2's federally backed OMAI compute cluster is now running on NVIDIA Blackwell Ultra hardware and has already shipped OLMo, Molmo 2, and MolmoAct models fully open to researchers.
ZAYA1-8B: Open Reasoning Model Rivals Claude on AMD GPUs
Zyphra's ZAYA1-8B matches Claude 4.5 Sonnet on HMMT 2025 math benchmarks at just 760M active parameters, trained entirely on AMD Instinct MI300X GPUs under Apache 2.0.
ZAYA1-8B
Zyphra's ZAYA1-8B is an 8.4B-parameter MoE reasoning model with only 760M active parameters that matches DeepSeek-R1-0528 on math and coding benchmarks while running at a fraction of the compute cost.
Agent Overload, Blind Attention, Unsafe Traces
Three new papers show that more agent components backfire, reasoning models hide unsafe thinking, and vision-language models waste most of their attention.
GPT-Realtime-2
OpenAI's second-generation real-time audio model with GPT-5-class reasoning, 128K context, five reasoning levels, and parallel tool calling - now generally available in the Realtime API.
OpenAI's Realtime API Goes GA with Three New Models
OpenAI's Realtime API exits beta with GPT-Realtime-2, Translate, and Whisper - three specialized voice models splitting reasoning, translation, and transcription into distinct endpoints.
MiniMax M2.7 Review: The Model That Trains Itself
MiniMax M2.7 is the first open-weight frontier model to automate 30-50% of its own training pipeline - but a controversial license change and sluggish speed complicate the story.
DeepMind's AlphaEvolve Recovered 0.7% of Google's Compute
Google DeepMind's May 2026 AlphaEvolve impact report shows the system running in production across infrastructure, quantum computing, genomics, and commercial partnerships spanning logistics to fintech.
