Back

Essays

Nov 2, 2026

Checking the rubrics: RIFT results on five public benchmarks

Ankit Aich
,
Derek Pham
,
Jonathan Schlosser
,
Charles Dickens
Oct 15, 2026

When partial credit opposes completion

Mehdi Fatemi
Oct 7, 2026

Frontier AI is accelerating. Open benchmarks need to keep up.

Vincent Sunn Chen
Sep 22, 2026

Data 2.0 and the research era of AI data

Alex Ratner
Aug 28, 2026

Terminal-Bench 4.0: why continuous benchmarks require continuous QA

Justin Bauer
Aug 24, 2026

Why frontier agents fail real engineering work: two Terminal-Bench 3.0 task deep dives

Derek Pham
,
Srikar Kodati
Aug 5, 2026

Milestone-based evaluation and training for long-horizon AI agents

Zhengyang (Jason) Qi
Aug 3, 2026

Enterprise environments and training AI agents for real-world workflows

Ramya Ramakrishnan
,
Joe Licata
,
Chris Glaze
Jun 29, 2026

Continual learning and evaluating how AI agents learn across sequences of tasks

Chris Glaze
Jun 15, 2026

Cua-Bench: benchmarking computer-use agents on professional software

Zhengyang (Jason) Qi
,
Armin Parchami