stablelm-tuned-alpha-3B: benchmark results
Stability AI's StableLM-Tuned-Alpha 3B, a NeoX-architecture chat model built on StableLM-Base-Alpha and fine-tuned on Alpaca, GPT4All, Anthropic HH and Databricks Dolly data, under a non-commercial license. Provider: Stability AI. Released 2023-04-19. Access: Open.
Aggregate Rating 1121 ± 13, rank #1641 of 1656 rated models, from 78 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| ToolBench - WebShop Long | 0 | Task Score | 44.2 |
| MMLU-by-task - Machine Learning | 31.25 | Accuracy (%) | 43.7 |
| MMLU-by-task - TruthfulQA MC2 | 42.33 | Accuracy (%) | 38.8 |
| MMLU-by-task - Business Ethics | 35 | Accuracy (%) | 34.3 |
| MMLU-by-task - Formal Logic | 26.19 | Accuracy (%) | 32.4 |
| MMLU-by-task - High School World History | 28.27 | Accuracy (%) | 27.9 |
| MMLU-by-task - TruthfulQA MC1 | 24.36 | Accuracy (%) | 26.8 |
| MMLU-by-task - Moral Scenarios | 24.25 | Accuracy (%) | 25.7 |
| MMLU-by-task - Medical Genetics | 30 | Accuracy (%) | 25.6 |
| ToolBench - WebShop Short | 0 | Task Score | 24.4 |
| MMLU-by-task - College Biology | 26.39 | Accuracy (%) | 23.7 |
| MMLU-by-task - Public Relations | 29.09 | Accuracy (%) | 23.1 |
Interactive version: theaggregate.ai/model?slug=stablelm-tuned-alpha-3b · How It Works · Data refreshed daily, snapshot 2026-10-20.