Research Benchmarks

Research Benchmarks

The instruments. When no existing benchmark measures the thing we built, we write one — and publish its tasks, its rubric and its recordings so someone else can run it.

A benchmark only its author can run is a press release. Every instrument here ships with the material required to reproduce it, and invites submissions from the systems it names.

1 publication

Research Benchmarks

Interactive Intelligence Benchmark

Every public benchmark for real-time voice scores the audio channel and, at most, whether a call was emitted. IIB-1 asks whether the artifact arrived on time, whether the referent resolved, and whether the agent told the truth about what it did.

Read →

All Research Benchmarks

Date	Category	Title
August 14, 2026	Research Benchmarks	Interactive Intelligence BenchmarkScoring what a real-time voice system does beyond the audio channel.

Join the research. Build frontier intelligences.

Labsintelligence is lab1 of Labs. We are a small research group working on speech‑to‑action, orchestration intelligence — speech‑to‑orchestration (STO) — and the interfaces that make both legible to a person.

Explore Research Roles →