τ²-bench (Telecom)

Customer-service agent simulation, telecom domain.

The best 3 · 3 models tested

Top 3 · best setting per model · 3 models, 3 results (0 independent)

Measured by independent testersIndependent Reported by the makerVendor-reported

τ²-bench (Telecom) leaderboard
				Thinking levelSetting
1	Gemini 3.1 Pro (Preview)	Google (Gemini / DeepMind)	99.3%	HighThinking (High)	Maker's own figureVendor-reportedGoogle ↗	—	19 Feb 2026
2	GPT-5.5	OpenAI	98.0%	Extra highreasoning effort=xhigh	Maker's own figureVendor-reportedOpenAI ↗	—	23 Apr 2026
3	GPT-5.4	OpenAI	92.8%	Extra highreasoning effort=xhigh	Maker's own figureVendor-reportedOpenAI ↗	—	23 Apr 2026