pythia-160m-deduped: benchmark results
Provider: EleutherAI. Access: Open.
Aggregate Rating 1118 ± 17, rank #10529 of 10916 rated models, from 73 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - High School Statistics | 47.22 | Accuracy (%) | 83.3 |
| MMLU-by-task - High School Physics | 32.45 | Accuracy (%) | 66 |
| MMLU-by-task - College Physics | 25.49 | Accuracy (%) | 53.2 |
| MMLU-by-task - TruthfulQA MC2 | 44.34 | Accuracy (%) | 48 |
| MMLU-by-task - High School Chemistry | 31.03 | Accuracy (%) | 43.8 |
| MMLU-by-task - Professional Medicine | 43.75 | Accuracy (%) | 39.7 |
| MMLU-by-task - Human Aging | 36.77 | Accuracy (%) | 32.1 |
| MMLU-by-task - Medical Genetics | 32 | Accuracy (%) | 31.5 |
| MMLU-by-task - High School Mathematics | 25.56 | Accuracy (%) | 29.5 |
| MMLU-by-task - Logical Fallacies | 29.45 | Accuracy (%) | 29.3 |
| MMLU-by-task - Electrical Engineering | 28.28 | Accuracy (%) | 28.1 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 44.34 | MC2 (%) (0-shot) | 26.8 |
Interactive version: theaggregate.ai/model?slug=pythia-160m-deduped · How It Works · Data refreshed daily, snapshot 2026-11-08.