BerryLM-v2-reasoning-budget-low: benchmark results
Provider: Other.
Aggregate Rating 1709 ± 39, rank #305 of 10916 rated models, from 23 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MERA - ruHHH | 92.13 | Accuracy (%) | 98.8 |
| MERA - LCS | 83.6 | Accuracy (%) | 98.6 |
| MERA | 0.81 | Total score | 97.6 |
| MERA - BPS | 99.9 | Accuracy (%) | 95.2 |
| MERA - MathLogicQA | 99.39 | Accuracy (%) | 95 |
| MERA - ruHateSpeech | 90.94 | Accuracy (%) | 94.5 |
| MERA - MaMuRAMu | 88.98 | Accuracy (%) | 94.3 |
| MERA - RWSD | 83.85 | Accuracy (%) | 94 |
| MERA - ruMMLU | 87.29 | Accuracy (%) | 93.8 |
| MERA - ruModAr | 99.77 | EM (%) | 93.8 |
| MERA - USE | 66.27 | Grade, normalized (%) | 93.3 |
| MERA - ruHumanEval | 66.22 | pass@1 (%) | 93.3 |
Interactive version: theaggregate.ai/model?slug=berrylm-v2-reasoning-budget-low · How It Works · Data refreshed daily, snapshot 2026-11-08.