THU, NOV 5, 2026 · UPDATED 23:14 UTC

TAG

Benchmarks

6 articles tagged “Benchmarks”, newest first.

Abstract illustration of a neural network

MODELS · Ai2

Ai2's StateBench finds frontier models fall to 13% or less on the hardest long state-tracking tasks

2 MIN READ · NOV 5, 2026

Abstract illustration of a top-ten risk list with the first item flagged

DEV TOOLS · Google

Google and Mercor's Physical-Engineering's Last Exam finds no AI agent passes half of real design tasks

2 MIN READ · NOV 4, 2026

Abstract illustration of a code editor where a flagged line is fixed

DEV TOOLS · Momentic

Momentic publishes QA Bench, a 1,396-bug test of QA agents in which its own Mo leads but misses most bugs

2 MIN READ · NOV 3, 2026

Abstract illustration of a top-ten risk list with the first item flagged

MODELS · Benchmarks

SemiAnalysis launches GDPx agent benchmark, where the top model scores 12%

2 MIN READ · NOV 2, 2026

Abstract illustration of a cursor filling in forms across app windows

MODELS · Video AI

Google-led researchers present StreamVibe, a video assistant that decides when to offer help

2 MIN READ · NOV 1, 2026

Abstract illustration of an open padlock in front of a grid of model weights

MODELS · DeepSeek

DeepSeek ships V4.1-Flash-1017, an MIT-licensed update focused on coding agents

2 MIN READ · OCT 28, 2026

NEWSLETTER · FREE

Your AI briefing, filtered by your interests

Every morning at 7 a.m. your local time, only the topics you choose. In English, French or Spanish.

Choose your topics

Products & launches Regulation & policy Models & research Developer tools Startups & funding + 5 more

One-click unsubscribe. We never sell your data.