BenchmarkActivecategory · agenticfamily · tau-bench · variant τ²

τ²-bench

dual-control tool-agent-user interaction (telecom, retail, airline)

quality51

Updated 32 min ago · first seen 11 Sept 2026

Metric: pass^1 · % ↑
Current results: 440
Models: 323
Current leader: Z.ai GLM 5.2 99.1%

Score history · nvidia-nemotron-nano-12b-v2-vl-reasoning 1 row

Not enough history to chart — a single observation (21.35% on 11 Sept 2026). Rows under different configurations count separately; the list below shows each one.

21.35%aa_slug=nvidia-nemotron-nano-12b-v2-vl-reasoning · evaluator=Artificial Analysis · index_version=4.311 Sept 2026

Back to the leaderboard

Frontier over time · pass^1 · evaluator=Artificial Analysis

2 leader changes recorded, all dated 11 Sept 2026 — the frontier line needs at least two distinct dates. The corpus is young: every result was first observed on the same day, so leader changes will separate in time as sources are re-crawled.

99.1%Z.ai GLM 5.2 Z.ai (Zhipu AI) Independent11 Sept 2026
90.3%grok-3-mini-reasoning SpaceXAI Independent11 Sept 2026

Includes closed rows (history). A point is emitted whenever a result beats every earlier result of the same group, ordered by evaluated_at when the source publishes it, else observed_at.

Leaderboard 323 models

Select models with +, then Compare.

No result in this group with these filters

Relax the trust / organization filters or pick another comparability group.

Definition

Task: Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 10 h agomedium
Metric: Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 10 h agomedium
Metric range: Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 32 min agomedium
Variant: Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 32 min agomedium
Harness: Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 32 min agomedium
Comparability note: Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 32 min agomedium
Paper: Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 10 h agomedium

Active group

pass^1 · evaluator=Artificial Analysis

323 models · 440 current rows

Comparability

Comparable same task and conditions · Partially comparable same task, conditions differ (effort, temperature, judge) · Not comparable different variant or metric

Also known as

τ²-bench, τ²-Bench Telecom, tau-squared bench, tau2 bench telecom, tau2-bench

slug tau2-bench · bench_01M293SPH15XRN6880KKHSKM5P

Rows are grouped by comparability group = canonical metric × config_key (hash of the task-defining configuration keys: variant, evaluator, harness, shots, pass regime…). A leaderboard shows one row per canonical model: its best current row inside the group. Reasoning effort, temperature or judge differences keep rows in the same group but mark them partially comparable. delta_rank compares with the ranking built from the closed (previous) rows of the same group.