Yi-1.5-9B-32K: benchmark results
01.AI's Yi-1.5 9B base model extended to a 32K-token context window, continually pretrained on the original Yi using a 500-billion-token high-quality corpus. Provider: 01.AI. Released 2024-05-13. Access: Open.
Aggregate Rating 1339 ± 15, rank #1412 of 1656 rated models, from 199 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 70.97 | Accuracy (%) (5-shot) | 94.5 |
| Open LLM Leaderboard - GPQA | 35.91 | Score | 90.4 |
| Open Korean LLM - Ko-GPQA-Diamond | 26.77 | Normalized accuracy (%) | 88.9 |
| Open Medical LLM - MMLU College Medicine | 67.63 | Accuracy (%) | 84.6 |
| Open Medical LLM - MMLU College Biology | 79.17 | Accuracy (%) | 79.7 |
| Open Portuguese LLM - OAB Exams | 50.11 | Accuracy (%) | 76 |
| MERA - ruCodeEval | 30.18 | pass@1 (%) | 73.8 |
| Open Chinese LLM - CMMLU | 63.02 | Accuracy (%) | 72.8 |
| Open Chinese LLM Leaderboard | 61.93 | Official Nonzero-Task Mean (%) | 72.8 |
| Open Medical LLM - MMLU Anatomy | 65.93 | Accuracy (%) | 71.4 |
| Open Chinese LLM - C-Eval Semantic | 80.95 | Accuracy (%) | 70.1 |
| MERA - ruHumanEval | 24.82 | pass@1 (%) | 68.9 |
Interactive version: theaggregate.ai/model?slug=yi-1-5-9b-32k · How It Works · Data refreshed daily, snapshot 2026-10-20.