Pythia-70M-ChatSalad: benchmark results
Provider: EleutherAI. Access: Open.
Aggregate Rating 1123 ± 17, rank #10476 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - TruthfulQA MC2 | 49.74 | Accuracy (%) | 75.3 |
| MMLU-by-task - High School Physics | 33.77 | Accuracy (%) | 75 |
| MMLU-by-task - College Physics | 27.45 | Accuracy (%) | 63 |
| MMLU-by-task - TruthfulQA MC1 | 27.78 | Accuracy (%) | 47.8 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 49.74 | MC2 (%) (0-shot) | 45.8 |
| MMLU-by-task - High School Chemistry | 30.05 | Accuracy (%) | 40.5 |
| MMLU-by-task - Logical Fallacies | 31.9 | Accuracy (%) | 34.8 |
| MMLU-by-task - High School Mathematics | 25.93 | Accuracy (%) | 34.1 |
| MMLU-by-task - High School Biology | 31.61 | Accuracy (%) | 33.1 |
| MMLU-by-task - Anatomy | 33.33 | Accuracy (%) | 32.1 |
| MMLU-by-task - Machine Learning | 28.57 | Accuracy (%) | 30.8 |
| MMLU-by-task - High School Statistics | 29.63 | Accuracy (%) | 30.3 |
Interactive version: theaggregate.ai/model?slug=pythia-70m-chatsalad · How It Works · Data refreshed daily, snapshot 2026-11-08.