Dialt
Get API key

Benchmarks

How Dialt compares.

Full-Duplex-Bench turn-taking is a measure of accuracy handling responses, pauses and interruptions. Every table includes the test date and model versions so results can be interpreted and reproduced as services change.

Full-Duplex-Bench (v1 + v1.5) 2026-08-19

Provider / modelFDB v1 pauseFDB v1 turn takingFDB v1.5 interruptionFDB v1.5 backchannelFDB avg
Dialt95.6100.0100.098.098.4
Qwen Audio 3.0 Realtime plus97.898.397.5100.098.4
GPT-Realtime-2.1 high95.698.394.094.995.7
GPT-Realtime-2 high99.3100.095.086.795.2
Grok Voice Think Fast 2.0 high97.890.897.094.995.1
Gemini 3.1 Flash Live high93.497.514.591.874.3

Scores 0–100, higher is better; FDB avg is the mean of the four gates; comparison rows are from the Artificial Analysis leaderboard (2026-08-14) at each model's flagship setting, and Dialt is measured on the same suites at our deployed configuration.

Coming up: voice-tau2 (agentic voice) benchmarks. Retail domain, regular and control speech complexity.