oasst-llama-13B-1000-steps: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1308 ± 15, rank #8586 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Abstract Algebra | 35 | Accuracy (%) | 87.4 |
| MMLU-by-task - Anatomy | 49.63 | Accuracy (%) | 75.9 |
| MMLU-by-task - Virology | 45.78 | Accuracy (%) | 73.2 |
| MMLU-by-task - Global Facts | 36 | Accuracy (%) | 70 |
| MMLU-by-task - HellaSwag | 61.66 | Accuracy (%) | 69.8 |
| MMLU-by-task - Professional Law | 40.42 | Accuracy (%) | 67.5 |
| MMLU-by-task - ARC Challenge | 54.44 | Accuracy (%) | 66.6 |
| MMLU-by-task - US Foreign Policy | 77 | Accuracy (%) | 65.8 |
| MMLU-by-task - Prehistory | 57.72 | Accuracy (%) | 65 |
| MMLU-by-task - Public Relations | 59.09 | Accuracy (%) | 63.1 |
| MMLU-by-task - High School World History | 70.89 | Accuracy (%) | 63 |
| MMLU-by-task - Econometrics | 29.82 | Accuracy (%) | 62.1 |
Interactive version: theaggregate.ai/model?slug=oasst-llama-13b-1000-steps · How It Works · Data refreshed daily, snapshot 2026-11-08.