oasst-sft-4-pythia-12B-epoch-3.5: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1150 ± 16, rank #9970 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - College Physics | 28.43 | Accuracy (%) | 67.4 |
| MMLU-by-task - ARC Challenge | 41.21 | Accuracy (%) | 35.7 |
| MMLU-by-task - Virology | 33.73 | Accuracy (%) | 35.3 |
| MMLU-by-task - Clinical Knowledge | 33.58 | Accuracy (%) | 34.6 |
| MMLU-by-task - Business Ethics | 35 | Accuracy (%) | 34.3 |
| MMLU-by-task - HellaSwag | 51.73 | Accuracy (%) | 33.8 |
| MMLU-by-task - Professional Law | 27.84 | Accuracy (%) | 33.1 |
| MMLU-by-task - High School US History | 29.41 | Accuracy (%) | 33 |
| MMLU-by-task - College Biology | 28.47 | Accuracy (%) | 30.5 |
| MMLU-by-task - High School European History | 28.48 | Accuracy (%) | 30.2 |
| MMLU-by-task - Professional Psychology | 27.78 | Accuracy (%) | 30 |
| MMLU-by-task - Anatomy | 31.85 | Accuracy (%) | 29.1 |
Interactive version: theaggregate.ai/model?slug=oasst-sft-4-pythia-12b-epoch-3-5 · How It Works · Data refreshed daily, snapshot 2026-11-08.