Ben Shi

Ben is on the Research team at Sierra. Previously, he was at Princeton University and Meta.

Publicaciones de Ben Shi

The text "τ³-Bench" on a blurry, grainy background of green and brown.

𝜏³-Bench: Advancing agent benchmarking to knowledge and voice

𝜏³-Bench is here. We've expanded agent evaluation to two new frontiers: knowledge retrieval and voice.

18 de marzo de 2026

Gradient image with voice and model icons

Improving voice performance with post-training

Post-training helps our customers' voice agents achieve shorter, clearer, and more human-like conversations.

12 de noviembre de 2025

Gradient mixed colors, t-bench and leaderboard icons

𝜏-Bench leaderboard: compare, explore, and understand agent performance

Introducing the 𝜏-Bench leaderboard — a community-driven platform where researchers can submit, verify, and compare results while exploring model behavior through interactive tools.

13 de octubre de 2025

Ben Shi

Publicaciones de Ben Shi

𝜏³-Bench: Advancing agent benchmarking to knowledge and voice

Improving voice performance with post-training

𝜏-Bench leaderboard: compare, explore, and understand agent performance

Descubra lo que Sierra puede hacer por usted

Publicaciones de Ben Shi

𝜏³-Bench: Advancing agent benchmarking to knowledge and voice

Improving voice performance with post-training

𝜏-Bench leaderboard: compare, explore, and understand agent performance