rwkv-4-7B-pile: benchmark results
Provider: RWKV. Access: Open.
Aggregate Rating 1137 ± 16, rank #10180 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Global Facts | 34 | Accuracy (%) | 58.4 |
| MMLU-by-task - Machine Learning | 32.14 | Accuracy (%) | 48.9 |
| MMLU-by-task - Medical Genetics | 37 | Accuracy (%) | 35.4 |
| MMLU-by-task - Professional Law | 27.51 | Accuracy (%) | 31.6 |
| MMLU-by-task - US Foreign Policy | 32 | Accuracy (%) | 29.4 |
| MMLU-by-task - Moral Disputes | 28.61 | Accuracy (%) | 29.1 |
| MMLU-by-task - HellaSwag | 48.89 | Accuracy (%) | 27.5 |
| MMLU-by-task - Business Ethics | 30 | Accuracy (%) | 26.7 |
| MMLU-by-task - Formal Logic | 24.6 | Accuracy (%) | 25.9 |
| MMLU-by-task - Professional Psychology | 26.96 | Accuracy (%) | 25.7 |
| MMLU-by-task - Virology | 30.12 | Accuracy (%) | 25.1 |
| MMLU-by-task - High School US History | 26.47 | Accuracy (%) | 24.7 |
Interactive version: theaggregate.ai/model?slug=rwkv-4-7b-pile · How It Works · Data refreshed daily, snapshot 2026-11-08.