Zarya-4B: benchmark results

Provider: Other. Released 2026-09-18. Access: Open.

Aggregate Rating 1435 ± 38, rank #4590 of 10552 rated models, from 17 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
MERA v2 - SAGE48.6Score (%)30.6
MERA v2 - Culture Specific16.6Score (%)20.4
MERA v2 - RussianRegions3.6Score (%)20.4
MERA v2 - Characters27.2Score (%)16.3
MERA v2 - GorillaHard4.8Score (%)12.2
MERA v2 - RUBIN26Score (%)12.2
MERA v2 - Agentic2.5Score (%)11.2
MERA v2 - Riddles5Score (%)11.2
MERA v20.08Total score10.2
MERA v2 - Human Centric7.4Score (%)10.2
MERA v2 - IFHardBench3.2Score (%)10.2
MERA v2 - LIMUR30.4Score (%)10.2

Interactive version: theaggregate.ai/model?slug=zarya-4b · How It Works · Data refreshed daily, snapshot 2026-11-16.