pythia-160m-deduped-step92k-193bt: benchmark results
Provider: EleutherAI. Access: Open.
Aggregate Rating 1123 ± 17, rank #10462 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - High School Mathematics | 28.89 | Accuracy (%) | 67.8 |
| MMLU-by-task - College Physics | 27.45 | Accuracy (%) | 63 |
| MMLU-by-task - Machine Learning | 34.82 | Accuracy (%) | 60.8 |
| MMLU-by-task - High School Statistics | 41.2 | Accuracy (%) | 58.8 |
| MMLU-by-task - Econometrics | 28.07 | Accuracy (%) | 47.3 |
| MMLU-by-task - TruthfulQA MC2 | 43.49 | Accuracy (%) | 43.8 |
| MMLU-by-task - Professional Medicine | 44.49 | Accuracy (%) | 42.8 |
| MMLU-by-task - Medical Genetics | 31 | Accuracy (%) | 29.8 |
| MMLU-by-task - Human Aging | 34.98 | Accuracy (%) | 29.3 |
| MMLU-by-task - US Foreign Policy | 30 | Accuracy (%) | 27 |
| MMLU-by-task - TruthfulQA MC1 | 24.36 | Accuracy (%) | 26.8 |
| MMLU-by-task - High School US History | 26.96 | Accuracy (%) | 26.7 |
Interactive version: theaggregate.ai/model?slug=pythia-160m-deduped-step92k-193bt · How It Works · Data refreshed daily, snapshot 2026-11-08.