Yi-9B: benchmark results
01.AI's Yi-9B, a bilingual base model in the Yi series trained from scratch on a 3T-token multilingual corpus. Provider: 01.AI. Released 2024-03-06. Access: Open.
Aggregate Rating 1401 ± 22, rank #1222 of 1656 rated models, from 31 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 70.06 | Accuracy (%) (5-shot) | 93.3 |
| Open LLM Leaderboard - GPQA | 31.8 | Score | 73.8 |
| Open Chinese LLM - C-Eval Semantic | 82.42 | Accuracy (%) | 72.8 |
| Open Chinese LLM - CMMLU | 61.66 | Accuracy (%) | 71.3 |
| Open Portuguese LLM - FaQuAD NLI | 74.79 | Macro F1 (%) | 71.3 |
| Open Portuguese LLM - OAB Exams | 47.84 | Accuracy (%) | 67.5 |
| Open Portuguese LLM - ENEM | 67.6 | Accuracy (%) | 67.4 |
| Open Chinese LLM - HellaSwag | 62.12 | Accuracy (%) | 66.1 |
| Open Chinese LLM - WinoGrande | 64.25 | Accuracy (%) | 65.5 |
| Open LLM Leaderboard v1 - GSM8K | 48.98 | Accuracy (%) (5-shot) | 62 |
| Open Portuguese LLM - BLUEX | 54.94 | Accuracy (%) | 61.9 |
| Open Chinese LLM Leaderboard | 58.34 | Official Nonzero-Task Mean (%) | 60.4 |
Interactive version: theaggregate.ai/model?slug=yi-9b · How It Works · Data refreshed daily, snapshot 2026-10-20.