BerryLM: benchmark results
Provider: Other.
Aggregate Rating 1588 ± 37, rank #1145 of 10916 rated models, from 23 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MERA - ruCodeEval | 78.41 | pass@1 (%) | 98.1 |
| MERA - ruHumanEval | 79.7 | pass@1 (%) | 97.6 |
| MERA - LCS | 77.4 | Accuracy (%) | 96.7 |
| MERA - ruModAr | 99.87 | EM (%) | 96.2 |
| MERA - ruMultiAr | 99.71 | EM (%) | 93.1 |
| MERA | 0.74 | Total score | 91.4 |
| MERA - MathLogicQA | 96.5 | Accuracy (%) | 86.7 |
| MERA - BPS | 99.5 | Accuracy (%) | 85.7 |
| MERA - ruHHH | 85.96 | Accuracy (%) | 81.1 |
| MERA - USE | 38.14 | Grade, normalized (%) | 78.1 |
| MERA - ruTiE | 85.87 | Accuracy (%) | 77.6 |
| MERA - MultiQ | 54.72 | F1 (%) | 76.8 |
Interactive version: theaggregate.ai/model?slug=berrylm · How It Works · Data refreshed daily, snapshot 2026-11-08.