ethzanalytics pythia-31m (BF16): benchmark results
Provider: Other.
Aggregate Rating 1132 ± 18, rank #10292 of 10916 rated models, from 62 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - TruthfulQA MC2 | 50.12 | Accuracy (%) | 76.5 |
| MMLU-by-task - High School Mathematics | 28.52 | Accuracy (%) | 64.7 |
| MMLU-by-task - Machine Learning | 30.36 | Accuracy (%) | 39 |
| MMLU-by-task - Formal Logic | 26.19 | Accuracy (%) | 32.4 |
| MMLU-by-task - High School Computer Science | 32 | Accuracy (%) | 31.3 |
| MMLU-by-task - TruthfulQA MC1 | 24.72 | Accuracy (%) | 30.4 |
| MMLU-by-task - US Foreign Policy | 33 | Accuracy (%) | 30.4 |
| MMLU-by-task - High School Statistics | 29.17 | Accuracy (%) | 29.1 |
| MMLU-by-task - College Physics | 21.57 | Accuracy (%) | 25.7 |
| MMLU-by-task - Marketing | 28.63 | Accuracy (%) | 24 |
| MMLU-by-task - High School Microeconomics | 25.21 | Accuracy (%) | 23.5 |
| MMLU-by-task - Anatomy | 28.15 | Accuracy (%) | 23.2 |
Interactive version: theaggregate.ai/model?slug=ethzanalytics-pythia-31m-bf16 · How It Works · Data refreshed daily, snapshot 2026-11-08.