BerryLM-MT: benchmark results
Provider: Other.
Aggregate Rating 1603 ± 37, rank #977 of 10916 rated models, from 23 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MERA - ruHumanEval | 81.1 | pass@1 (%) | 98.6 |
| MERA - ruMultiAr | 100 | EM (%) | 98.6 |
| MERA - LCS | 82.4 | Accuracy (%) | 98.1 |
| MERA - ruCodeEval | 77.74 | pass@1 (%) | 97.6 |
| MERA - ruModAr | 99.9 | EM (%) | 97.2 |
| MERA | 0.75 | Total score | 91.9 |
| MERA - MathLogicQA | 98.86 | Accuracy (%) | 89.5 |
| MERA - ruTiE | 87.42 | Accuracy (%) | 86.2 |
| MERA - BPS | 99.4 | Accuracy (%) | 83.8 |
| MERA - ruMMLU | 77.68 | Accuracy (%) | 80 |
| MERA - USE | 38.92 | Grade, normalized (%) | 79.5 |
| MERA - ruHHH | 85.39 | Accuracy (%) | 79.4 |
Interactive version: theaggregate.ai/model?slug=berrylm-mt · How It Works · Data refreshed daily, snapshot 2026-11-08.