pythia-70m-deduped-step44k-92bt: benchmark results
Provider: EleutherAI. Access: Open.
Aggregate Rating 1128 ± 17, rank #10357 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - High School Statistics | 47.22 | Accuracy (%) | 83.3 |
| MMLU-by-task - TruthfulQA MC2 | 46.12 | Accuracy (%) | 56 |
| MMLU-by-task - High School Physics | 29.8 | Accuracy (%) | 46.5 |
| MMLU-by-task - Professional Medicine | 44.49 | Accuracy (%) | 42.8 |
| MMLU-by-task - College Physics | 23.53 | Accuracy (%) | 41.6 |
| MMLU-by-task - Moral Scenarios | 24.69 | Accuracy (%) | 38.9 |
| MMLU-by-task - College Chemistry | 29 | Accuracy (%) | 38 |
| MMLU-by-task - High School Geography | 35.86 | Accuracy (%) | 33.8 |
| MMLU-by-task - TruthfulQA MC1 | 25.09 | Accuracy (%) | 33.5 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 46.12 | MC2 (%) (0-shot) | 33.5 |
| MMLU-by-task - High School Biology | 31.61 | Accuracy (%) | 33.1 |
| MMLU-by-task - Security Studies | 35.51 | Accuracy (%) | 32.8 |
Interactive version: theaggregate.ai/model?slug=pythia-70m-deduped-step44k-92bt · How It Works · Data refreshed daily, snapshot 2026-11-08.