Yi-1.5-9B Chat — benchmark results
01.AI's Apache-2.0 9B chat model from the Yi-1.5 series (May 2024), continually pretrained on 500B extra tokens and tuned on 3M samples. Provider: 01.AI. Released 2024-05-13. Access: Open.
Unified ELO 1416 ± 15, rank #1148 of 1776 rated models, from 62 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LatamBoard - Spanish MGSM | 18.8 | Score (%) | 93.9 |
| Mobile-MMLU | 72.7 | Overall Accuracy (%) | 90.5 |
| LA Leaderboard - Spanish Law Exams | 39.5 | Accuracy (%) | 88.2 |
| Open Chinese LLM - GSM8K | 64.22 | Accuracy (%) | 88.1 |
| LatamBoard - Spanish Escola | 71.04 | Score (%) | 87.9 |
| LatamBoard - Spanish PAWS | 63 | Score (%) | 86.4 |
| LatamBoard - Spanish TeleIA | 71.43 | Score (%) | 86.4 |
| Open CoT - LogiQA | 7.51 | CoT Gain (%) | 85.9 |
| Open LLM Leaderboard - GPQA | 11.3 | Score | 82.3 |
| LatamBoard - FaQuAD NLI | 76.18 | Score (%) | 78.8 |
| Open Chinese LLM Leaderboard | 64.07 | Average Score (%) | 78 |
| Open CoT - LSAT Analytical Reasoning | 6.09 | CoT Gain (%) | 76.7 |
Interactive version: theaggregate.ai/model?slug=yi-1-5-9b-chat · How the rankings work · Data refreshed daily, snapshot 2026-07-22.