Yi Large (Preview): benchmark results
Preview of 01.AI's Yi-Large, an API-only flagship (June 2024). Provider: 01.AI. Released 2024-06-17. Access: API.
Aggregate Rating 1572 ± 18, rank #1371 of 10916 rated models, from 91 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| HELM MMLU - Public Relations | 82.73 | EM | 98.1 |
| HELM MMLU - Computer Security | 86 | EM | 94.9 |
| BenchBench | 87.14 | Aggregate Score (%) | 94.1 |
| WildBench | 55.29 | WB Score Task-Macro | 93.5 |
| HELM MMLU - Anatomy | 82.96 | EM | 92.3 |
| HELM MMLU - College Medicine | 82.66 | EM | 91.7 |
| HELM MMLU - Econometrics | 72.81 | EM | 89.7 |
| HELM MMLU - Moral Scenarios | 83.13 | EM | 89.7 |
| HELM MMLU - Virology | 59.04 | EM | 89.7 |
| AlpacaEval 2.0 | 51.89 | LC Win Rate (%) | 88.3 |
| HELM MMLU - Human Sexuality | 90.08 | EM | 84 |
| HELM Lite - OpenbookQA | 94.6 | Exact Match (%) | 83.9 |
Interactive version: theaggregate.ai/model?slug=yi-large-preview · How It Works · Data refreshed daily, snapshot 2026-11-08.