pythia-31m-goodwiki-deduped-2048-scratch: benchmark results
Provider: EleutherAI. Access: Open.
Aggregate Rating 1116 ± 17, rank #10559 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - TruthfulQA MC2 | 51.32 | Accuracy (%) | 82.4 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 51.32 | MC2 (%) (0-shot) | 51.6 |
| MMLU-by-task - Machine Learning | 31.25 | Accuracy (%) | 43.7 |
| MMLU-by-task - Formal Logic | 28.57 | Accuracy (%) | 41.7 |
| MMLU-by-task - TruthfulQA MC1 | 24.97 | Accuracy (%) | 32.8 |
| MMLU-by-task - World Religions | 32.16 | Accuracy (%) | 28 |
| MMLU-by-task - Business Ethics | 30 | Accuracy (%) | 26.7 |
| MMLU-by-task - Marketing | 29.06 | Accuracy (%) | 26.1 |
| MMLU-by-task - College Physics | 21.57 | Accuracy (%) | 25.7 |
| MMLU-by-task - Medical Genetics | 30 | Accuracy (%) | 25.6 |
| MMLU-by-task - US Foreign Policy | 28 | Accuracy (%) | 22.2 |
| MMLU-by-task - Human Aging | 31.39 | Accuracy (%) | 21.7 |
Interactive version: theaggregate.ai/model?slug=pythia-31m-goodwiki-deduped-2048-scratch · How It Works · Data refreshed daily, snapshot 2026-11-08.