RuadaptQwen-32B-instruct: benchmark results
Provider: Other.
Aggregate Rating 1586 ± 35, rank #1171 of 10916 rated models, from 23 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MERA - ruHateSpeech | 87.17 | Accuracy (%) | 88.1 |
| MERA - PARus | 92.4 | Accuracy (%) | 84.6 |
| MERA - ruCodeEval | 42.56 | pass@1 (%) | 82.4 |
| MERA - ruTiE | 86.62 | Accuracy (%) | 81.9 |
| MERA - ruHumanEval | 38.9 | pass@1 (%) | 80.4 |
| MERA - ruWorldTree | 98.48 | Accuracy (%) | 80.2 |
| MERA - ruDetox | 31.63 | Joint Score (%) | 78.9 |
| MERA - MultiQ | 55.05 | F1 (%) | 78.2 |
| MERA - RWSD | 63.85 | Accuracy (%) | 77.6 |
| MERA - ruHHH | 84.83 | Accuracy (%) | 77.5 |
| MERA - BPS | 98.4 | Accuracy (%) | 75.2 |
| MERA - MathLogicQA | 72.62 | Accuracy (%) | 75.2 |
Interactive version: theaggregate.ai/model?slug=ruadaptqwen-32b-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.