Skip to content
ENTITY PROFILE / KNOWLEDGE GRAPH

τ²‑bench

RSS

ALTK‑Evolve outperforms the retail entries on τ²‑bench, ranking top on the leader board snapshot GPT‑4.1 is used as the agent model in τ²‑bench tasks GPT‑5.5 is used as the customer‑simulator model in τ²‑bench tasks· Entity summary generated by Graphiti

RELATIONS
3Relations
CURRENT
3Current
EVENTS
1Events
REPORTS
1Source reports
KNOWLEDGE ATLAS0 entities · 0 relations
No public neighbors yet
Explore all published links of a node; previously discovered relations remain visible.

Relation timeline

BY VALID-FROM DATE
  1. GPT-5.5USED AS CUSTOMER SIMULATOR INτ²‑bench

    GPT‑5.5 is used as the customer‑simulator model in τ²‑bench tasks

    Current1 sourceGPT-5.5
  2. ALTK-EvolveOUTPERFORMSτ²‑bench

    ALTK‑Evolve outperforms the retail entries on τ²‑bench, ranking top on the leader board snapshot

    Current1 sourceALTK-Evolve
  3. GPT‑4.1USED AS AGENT MODEL INτ²‑bench

    GPT‑4.1 is used as the agent model in τ²‑bench tasks

    Current1 sourceGPT‑4.1

Relations are facts Graphiti extracted from reports, not verbatim quotes. An end date means later reporting showed the relation no longer holds.

Events 1

Source reports 1