AI EVALUATION, IN CONTEXT.BY EQUALITY MACHINE

Model reports

tau2-bench

Per-domain scores (Retail, Telecom, Airline) diverge sharply and several cards apply the Airline domain fixes from the Claude Opus 4.5 system card, so an average conceals both the domain mix and the patch level.

评测信息与证据

来源
Model reports
发布者
未收录
评测发布日期
2025-06-09
采集日期
未收录
模态
未收录

本站保留来源报告的结果,不代表独立复测。请先核对任务版本、评测协议、分数单位和报告日期;不同运行条件不能直接合并为统一排名。

原始资料

报告成绩 5

按来源中的观察顺序展示,顺序不代表排名。日期保留原始精度。

模型数值单位协议报告日期与口径来源
Gemini 3.1 Pro90.8percentThinking (High), Retail2026-02-19 · document_publicationGemini 3.1 Pro
Gemini 3.1 Pro99.3percentThinking (High), Telecom2026-02-19 · document_publicationGemini 3.1 Pro
Gemma 4 (31B)76.9percentaverage over 32026-03-11 · document_publicationGemma 4 (31B)
Qwen3.5-397B-A17B86.7percentthinking (temp 0.6, top_p 0.95, top_k 20)2026-02-16 · document_publicationQwen3.5-397B-A17B
GLM-589.7percentRetail and Telecom prompt adjustment; Airline domain fixes per Claude Opus 4.5 system card2026-02-11 · document_publicationGLM-5