Published benchmarks · Last run

Benchmarked against the tools your platforms actually run on.

We publish and maintain benchmarks for every claim we make - scored head to head against the engagement platforms you already pay for, the cloud AI services they run on, and the AI assistants on your desktop. Every number traces to a published results file, and the full evidence pack is available for technical review.

Want to check our work? Request the benchmark pack - test data, scoring code, raw outputs, and methodology notes.

Benchmark suites

Aspect-based sentiment (ABSA) v1.0 · Last run

Issue-level sentiment analysis

Every issue in every response, with its own sentiment, filed under your reporting topics.

See the full benchmark

Issues found in long written submissions

Communiti
100%
Amazon Comprehend
33%

Issues implied but never named

Communiti
90%
Amazon Comprehend
1%

Issues correctly filed under your reporting topics

Communiti
93%
AI assistant
5%

How we benchmark

Numbers you can take to your IT and governance teams

Benchmarks are only useful if you can check them. Ours are built to be checked - and to be rerun when the products change.

Synthetic test data, no resident data

Every corpus is written for testing - spanning typos, sarcasm, voice transcripts, low-literacy writing, implied issues, and ten community languages.

Best-foot-forward for competitors

Competing tools are scored on their best-performing configuration, with identical matching rules, only on content they support.

Reproducible end to end

Every number traces to a published results file, and the full evaluation suite re-runs end to end - including a non-live path that re-scores cached outputs.

Evidence pack on request

Test data, scoring code, raw model outputs, charts, and methodology notes are available for technical review by your IT and AI governance teams.

See your own consultation benchmarked this way

Bring one real, de-identified feedback export to a 30-minute walkthrough and compare the results against your current tooling.

Stay close to the future of community engagement

Product notes, practical field guides, and evidence-led thinking for teams working under public scrutiny.

Read about ourWe care about your data in our privacy policy.

End-to-end engagement workflow