oasst-pythia-12B-flash-attn-5000-steps: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1147 ± 17, rank #10012 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Abstract Algebra | 34 | Accuracy (%) | 82 |
| MMLU-by-task - College Physics | 29.41 | Accuracy (%) | 71.1 |
| MMLU-by-task - High School Physics | 31.13 | Accuracy (%) | 56.1 |
| MMLU-by-task - Moral Scenarios | 25.47 | Accuracy (%) | 48.6 |
| MMLU-by-task - Global Facts | 32 | Accuracy (%) | 44.3 |
| MMLU-by-task - Elementary Mathematics | 27.25 | Accuracy (%) | 41.4 |
| MMLU-by-task - ARC Challenge | 42.24 | Accuracy (%) | 37.2 |
| MMLU-by-task - HellaSwag | 52.71 | Accuracy (%) | 35.1 |
| MMLU-by-task - High School Mathematics | 25.93 | Accuracy (%) | 34.1 |
| MMLU-by-task - High School US History | 29.41 | Accuracy (%) | 33 |
| MMLU-by-task - Clinical Knowledge | 31.7 | Accuracy (%) | 32.7 |
| MMLU-by-task - Astronomy | 30.92 | Accuracy (%) | 32.4 |
Interactive version: theaggregate.ai/model?slug=oasst-pythia-12b-flash-attn-5000-steps · How It Works · Data refreshed daily, snapshot 2026-11-08.