τ²-bench
dual-control tool-agent-user interaction (telecom, retail, airline)
Updated 28 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 · Olmo-3-7B-Instruct 1 row
Not enough history to chart — a single observation (12.57% on 11 Sept 2026). Rows under different configurations count separately; the list below shows each one.
- 12.57%aa_slug=olmo-3-7b-instruct · evaluator=Artificial Analysis · index_version=4.311 Sept 2026
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.
One row per canonical model — its best current row inside this comparability group (effort variants are folded into the model). Bars are relative to the page's best score. “vs leader” reads comparability: partially comparable = same task, conditions differ (reasoning effort, temperature, judge). Rules →