StableLM Tuned Alpha 7B — benchmark results
Provider: Stability AI. Released 2023-04-25. Access: Open.
Unified ELO 1116 ± 19, rank #1756 of 1776 rated models, from 79 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - College Physics | 25.49 | Accuracy (%) | 53.1 |
| ToolBench - WebShop Long | 0 | Task Score | 44.2 |
| MMLU-by-task - High School Statistics | 35.19 | Accuracy (%) | 42.3 |
| MMLU-by-task - College Mathematics | 30 | Accuracy (%) | 38.1 |
| MMLU-by-task - College Chemistry | 28 | Accuracy (%) | 35 |
| MMLU-by-task - High School Mathematics | 25.93 | Accuracy (%) | 34 |
| MMLU-by-task - Human Sexuality | 29.01 | Accuracy (%) | 31.1 |
| MMLU-by-task - Human Aging | 35.43 | Accuracy (%) | 30.1 |
| MMLU-by-task - High School World History | 28.69 | Accuracy (%) | 29.4 |
| MMLU-by-task - TruthfulQA MC2 | 40.37 | Accuracy (%) | 28.7 |
| MMLU-by-task - Conceptual Physics | 31.49 | Accuracy (%) | 28.4 |
| MMLU-by-task - Jurisprudence | 28.7 | Accuracy (%) | 27.2 |
Interactive version: theaggregate.ai/model?slug=stablelm-tuned-alpha-7b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.