rwkv-4-3B-pile: benchmark results
Provider: RWKV. Access: Open.
Aggregate Rating 1132 ± 15, rank #10291 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Machine Learning | 30.36 | Accuracy (%) | 39 |
| MMLU-by-task - Business Ethics | 34 | Accuracy (%) | 33.2 |
| MMLU-by-task - Formal Logic | 26.19 | Accuracy (%) | 32.4 |
| MMLU-by-task - High School World History | 29.11 | Accuracy (%) | 30.2 |
| MMLU-by-task - Global Facts | 30 | Accuracy (%) | 30 |
| MMLU-by-task - Jurisprudence | 29.63 | Accuracy (%) | 29.6 |
| MMLU-by-task - Human Aging | 34.98 | Accuracy (%) | 29.3 |
| MMLU-by-task - Virology | 31.33 | Accuracy (%) | 28.1 |
| MMLU-by-task - College Chemistry | 25 | Accuracy (%) | 27.3 |
| MMLU-by-task - Prehistory | 28.4 | Accuracy (%) | 26.2 |
| MMLU-by-task - Public Relations | 30 | Accuracy (%) | 24.9 |
| MMLU-by-task - High School Biology | 27.1 | Accuracy (%) | 24.1 |
Interactive version: theaggregate.ai/model?slug=rwkv-4-3b-pile · How It Works · Data refreshed daily, snapshot 2026-11-08.