Watari-7B-v1: benchmark results
Provider: Other.
Aggregate Rating 1436 ± 35, rank #4365 of 10916 rated models, from 23 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MERA - RWSD | 59.23 | Accuracy (%) | 65.7 |
| MERA - ruDetox | 21.27 | Joint Score (%) | 54.5 |
| MERA - MathLogicQA | 45.49 | Accuracy (%) | 46 |
| MERA - ruWorldTree | 87.62 | Accuracy (%) | 45.2 |
| MERA - ruOpenBookQA | 78.75 | Accuracy (%) | 44.8 |
| MERA - USE | 15.98 | Grade, normalized (%) | 43.8 |
| MERA - CheGeKa | 11.05 | F1 (%) | 43.6 |
| MERA - PARus | 77.4 | Accuracy (%) | 43.4 |
| MERA - MaMuRAMu | 64.85 | Accuracy (%) | 43.3 |
| MERA - ruMMLU | 53.91 | Accuracy (%) | 43.3 |
| MERA - ruHHH | 65.73 | Accuracy (%) | 41.1 |
| MERA - ruHateSpeech | 67.55 | Accuracy (%) | 41 |
Interactive version: theaggregate.ai/model?slug=watari-7b-v1 · How It Works · Data refreshed daily, snapshot 2026-11-08.