Agentic · tools

τ²-Bench Telecom leaderboard

Name: benchgap: LLM benchmark scores, measured and estimated
Creator: benchgap

As of 2026-10-07, the highest measured score on τ²-Bench Telecom is 99.1% by GLM-5.2 (max).

#	Model	Score	Source
1	GLM-5.2 (max)	99.1%	measured
2	JT-35B-Flash	99.1%	measured
3	GLM-4.7-Flash	98.8%	measured
4	Claude Fable 5 (with fallback)	98.5%	measured
5	GLM-5-Turbo	98.5%	measured
6	MiniMax-M3	88.9%	measured
7	Nemotron 3 Ultra	83.3%	measured

All leaderboards