MERA — a benchmark ecosystem for Russian-language AI models

MERA is an independent, reproducible model evaluation framework for Russian-language tasks: from language and code to multimodal and industry applications.

Everything you need to evaluate models — in one place

Find benchmarks reviewed by industry experts, compare models on leaderboards, and explore tasks and evaluation methods.

5100+private submissions

700+public submissions

500+evaluated models

400+users

20+industry partners

Find a benchmark

Partner benchmarks covering text, code, multimodality, industry applications, agents, and more.

Diverse, representative evaluation

Explore the methodology

An open protocol: tasks, metrics, data, and limitations. Every benchmark is reviewed by experts.

Reviewed by experts

Compare models

Live leaderboards for each skill. Compare state-of-the-art open and closed models in a single ranking.

Open and closed models

Add your benchmark

Propose a test — experts will review it for inclusion in the open standard for Russian-language models.

Community review

Partners and participants

Uniting leaders for the future of technology

The Alliance for Artificial Intelligence is a unique organization created to unite the efforts of leading technology companies, researchers and experts. Our mission is to accelerate the development and implementation of artificial intelligence in the key areas, such as education, science and business.

Learn More

News

See all All

01 Sep 2026

AI Alliance Launches MERA Text 2.0, a New Leaderboard for Evaluating Text Language Models

The update introduces 12 new private tests grouped into four categories: Human-Centric, Culture-Specific, Agentic, and Reasoning.

24 Jul 2026

The AI Alliance has launched an open leaderboard to evaluate models’ reasoning capabilities in Russian.

The AI Alliance has launched the open MERA Reason leaderboard to evaluate the ability of modern language models to reason in Russian. The platform brings together four sets of mathematical and logical problems and enables models to be compared in a unified, reproducible environment.

24 Sep 2025

AI Alliance Launches Dynamic SWE-MERA Benchmark for Evaluating Code Models

The AI Alliance's benchmark lineup has been expanded with a new tool — the dynamic benchmark SWE-MERA, designed for comprehensive evaluation of coding models on tasks close to real development conditions. SWE-MERA was created as a result of collaboration among leading Russian AI teams: MWS AI (part of MTS Web Services), Sber, and ITMO University.