τ-bench

Source-qualified evaluations, report statistics and safety observations.

xai-realtime

MetricValueUnit
τ-bench · banking_knowledge · pass^10.1649484536082474percent

grok-voice-fast-1.0

MetricValueUnit
τ-bench · airline · pass^10.36percent
τ-bench · retail · pass^10.386percent
τ-bench · telecom · pass^10.40399999999999997percent

gemini-3.8-live-extended-thinking

MetricValueUnit
τ-bench voice aggregate0.3384879725085911percent

gemini-3.8-live-extended-thinking

MetricValueUnit
τ-bench voice aggregate0.4375percent

grok-voice-think-fast-2.0

MetricValueUnit
τ-bench voice aggregate0.10996563573883161percent

grok-voice-think-fast-2.0

MetricValueUnit
τ-bench voice aggregate0.44166666666666665percent

gemini-3.8-live-extended-thinking

MetricValueUnit
τ-bench voice aggregate0.6850793650793651percent

grok-voice-think-fast-2.0

MetricValueUnit
τ-bench voice aggregate0.7136961451247166percent

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace