rwkv-4-169m-pile: benchmark results
Provider: RWKV. Access: Open.
Aggregate Rating 1113 ± 17, rank #10589 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - College Physics | 23.53 | Accuracy (%) | 41.6 |
| MMLU-by-task - Moral Scenarios | 24.58 | Accuracy (%) | 36.2 |
| MMLU-by-task - TruthfulQA MC2 | 41.92 | Accuracy (%) | 36 |
| MMLU-by-task - Professional Accounting | 28.72 | Accuracy (%) | 35.6 |
| MMLU-by-task - Machine Learning | 29.46 | Accuracy (%) | 35.2 |
| MMLU-by-task - Business Ethics | 33 | Accuracy (%) | 32 |
| MMLU-by-task - World Religions | 32.16 | Accuracy (%) | 28 |
| MMLU-by-task - Econometrics | 25.44 | Accuracy (%) | 26.9 |
| MMLU-by-task - Jurisprudence | 26.85 | Accuracy (%) | 22.3 |
| MMLU-by-task - Marketing | 27.78 | Accuracy (%) | 21.9 |
| MMLU-by-task - Formal Logic | 23.02 | Accuracy (%) | 20.4 |
| MMLU-by-task - Global Facts | 26 | Accuracy (%) | 19.5 |
Interactive version: theaggregate.ai/model?slug=rwkv-4-169m-pile · How It Works · Data refreshed daily, snapshot 2026-11-08.