oasst-pythia-12B-pretrained-sft: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1149 ± 17, rank #9981 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - College Physics | 34.31 | Accuracy (%) | 86.4 |
| MMLU-by-task - High School Physics | 30.46 | Accuracy (%) | 50.8 |
| MMLU-by-task - Formal Logic | 30.16 | Accuracy (%) | 48.8 |
| MMLU-by-task - Moral Scenarios | 25.47 | Accuracy (%) | 48.6 |
| MMLU-by-task - Professional Medicine | 44.49 | Accuracy (%) | 42.8 |
| MMLU-by-task - Abstract Algebra | 28 | Accuracy (%) | 39.6 |
| MMLU-by-task - Econometrics | 27.19 | Accuracy (%) | 39.6 |
| MMLU-by-task - Security Studies | 40 | Accuracy (%) | 39.1 |
| MMLU-by-task - Business Ethics | 40 | Accuracy (%) | 38.5 |
| MMLU-by-task - Global Facts | 31 | Accuracy (%) | 36.8 |
| MMLU-by-task - ARC Challenge | 40.61 | Accuracy (%) | 34.8 |
| MMLU-by-task - Electrical Engineering | 31.03 | Accuracy (%) | 34.2 |
Interactive version: theaggregate.ai/model?slug=oasst-pythia-12b-pretrained-sft · How It Works · Data refreshed daily, snapshot 2026-11-08.