Workload

interactive-assistant-v1

released

Question it answers

Is single-user streaming chat responsive on this system?

What is measured

Client-side TTFT, inter-token latency and end-to-end time over a frozen 16-item EN+RU corpus in three length bands; format, language and repetition gates with per-item expectations.

Claims this workload cannot support

“Supports N employees”, production capacity claims.

Frozen identity

Every released workload revision freezes its item hashes, load model and quality gates. Results reference the exact revision; changing any identity field creates a new revision. The facts below are read from the catalog file, not typed into this page.

Revision
2026-08-02
Load model
closed_loop
Quality gates
format_gate, language_gate, repetition_gate
Metrics contract
ttft_ms, inter_token_latency_ms, e2e_ms
Corpus hash
7664391d8321…
← Workload library