MERA Original Paper - ruMultiAr: leaderboard
Metric: Exact Match (%; 5-shot, greedy generation). Source: arxiv.org. Saturation forecast: Estimated already saturated. 19 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Mistral-7B-v0.1 | 19.5 |
| 2 | Yi 6B (Base) | 18.9 |
| 3 | davinci-002 | 17.6 |
| 4 | Llama 2 13B Base | 15.6 |
| 5 | Llama 2 7B Base | 12.4 |
| 6 | ruGPT-3.5 | 2.5 |
| 7 | mGPT-13B | 1.9 |
| 8 | mGPT | 1.2 |
| 9 | ruGPT-3 (Medium) | 1.2 |
| 10 | ruGPT-3-small | 0.9 |
| 11 | ruGPT3-large | 0.7 |
| 12 | ruT5-base | 0 |
Interactive version: theaggregate.ai/benchmark?slug=mera-original-paper-rumultiar · How It Works · Data refreshed daily, snapshot 2026-09-25.