Gemini API model id gemini-3-pro-preview; default sampling settings. Gemini results are pass@1 and single-attempt unless specified; smaller benchmarks average multiple trials.
未知项
The evaluation table does not specify a thinking budget or inference-time compute setting.
工具
工具条件未记录
推理预算
未记录
框架
Sierra framework
协议
Average across Retail, Airline and Telecom; standard Sierra framework with prompt adjustment and Gemini user model.
条件
Three category results are also published separately.
Gemini 3 Pro · tau2-bench · Average across Retail, Airline and Telecom categories · Scores and configurations
Gemini 3 Pro record for tau2-bench · Average across Retail, Airline and Telecom categories. 1 score record for this release, including 1 exact value (may include historical records). Includes 1 source location.
Gemini 3 Pro · tau2-bench scores and configurations
Metric and score
Configuration and evaluation conditions
Sources
Average score85.4%Reported 85.4% · Unit %
Published Unconfirmed
Gemini 3 Pro API default
Settings
Gemini API model id gemini-3-pro-preview; default sampling settings. Gemini results are pass@1 and single-attempt unless specified; smaller benchmarks average multiple trials.
Unknowns
The evaluation table does not specify a thinking budget or inference-time compute setting.
Tools
Tool access not recorded
Reasoning budget
not recorded
Framework
Sierra framework
Protocol
Average across Retail, Airline and Telecom; standard Sierra framework with prompt adjustment and Gemini user model.
Conditions
Three category results are also published separately.