Sarashina2.2-V-3B: benchmark results
Provider: Other.
Aggregate Rating 1499 ± 48, rank #2366 of 10916 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| JMMMU-Pro - Culture Specific | 54 | Accuracy (%) | 84.6 |
| JMMMU-Pro - Japanese Art | 48 | Accuracy (%) | 84.6 |
| JMMMU-Pro - Japanese Heritage | 51.33 | Accuracy (%) | 84.6 |
| JMMMU-Pro - Japanese History | 51.33 | Accuracy (%) | 84.6 |
| JMMMU-Pro | 42.88 | Overall (percent) | 69.2 |
| JMMMU-Pro - Culture Agnostic | 36.25 | Accuracy (%) | 69.2 |
| JMMMU-Pro - Overall | 42.88 | Accuracy (%) | 69.2 |
| JMMMU-Pro - World History | 65.33 | Accuracy (%) | 69.2 |
| HakushoBench (Direct) | 37.7 | Accuracy (%), direct prompt (answer accurately and concisely | 28.6 |
| HakushoBench (CoT) | 32.3 | Accuracy (%), chain-of-thought prompt (think step by step, t | 0 |
Interactive version: theaggregate.ai/model?slug=sarashina2-2-v-3b · How It Works · Data refreshed daily, snapshot 2026-11-08.