Benchmark-proven

Azerbaijani ability, measured — not claimed

Prometheus is validated on the TUMLU benchmark: 38,139 native Azerbaijani questions across 11 academic disciplines, with no translated content, so its ability is proven rather than asserted.

Overview

TUMLU-validated

It is easy to claim a model speaks Azerbaijani; it is harder to prove it. Prometheus is validated on TUMLU, a benchmark of 38,139 genuinely native Azerbaijani questions spanning 11 academic disciplines — no translated questions — so its Azerbaijani ability is measured against real, native material.

What it does

Evidence, not marketing

Validated on the TUMLU benchmark of native Azerbaijani questions.

38,139 questions across 11 academic disciplines.

No translated content — every question is genuinely native.

Provides an objective measure of Azerbaijani ability.

Backs a model built natively for Azerbaijani and run on your own infrastructure.

How it works

How it is validated

1Native Azerbaijani questions are drawn from 11 disciplines
2Prometheus answers all 38,139 questions
3Results measure real Azerbaijani ability
4No translated content skews the score
FAQ

Common questions

What is TUMLU?

TUMLU is a benchmark of 38,139 native Azerbaijani questions across 11 academic disciplines, used to measure a model’s real Azerbaijani ability.

Are the questions translated from English?

No. The benchmark uses genuinely native Azerbaijani questions, with no translated content.

Why does the benchmark matter?

It replaces marketing claims with an objective measure of how well the model actually handles native Azerbaijani across many disciplines.

Explore more

More of what Prometheus does

Get started

See Prometheus on your own infrastructure

Request a demo to see Prometheus running on-premise — Azerbaijani understanding, model sizing and API integration, end to end.