Benchmarks

τ²-Bench Telecom

Agentsunit % · normalized over [30, 99]

τ²-Bench telecom domain — dual-control tool-agent-user tasks in a simulated telecom support setting; a harder successor to tau-bench, distinct scale.

#ModelSourceScoreNormalized

Score distribution

38 tracked results across the normalization window

3099

Score vs. parameters

Open-weights models, log-x params