Yi-1.5-9B-Chat-16K: benchmark results
01.AI's Apache-2.0 9B Yi-1.5 chat model (2024) extended to a 16K context window. Provider: 01.AI. Released 2024-05-15. Access: Open.
Aggregate Rating 1423 ± 14, rank #1135 of 1656 rated models, from 106 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SuperCLUE-DSPSafeBench - Overall | 79.37 | Score | 100 |
| Open LLM Leaderboard v1 - MMLU | 70.96 | Accuracy (%) (5-shot) | 94.5 |
| Open Korean LLM - Ko-IFEval | 43.12 | Strict accuracy, prompt/instruction mean (%) | 87.6 |
| Open Chinese LLM - GSM8K | 59.97 | Accuracy (%) | 84.3 |
| Open Korean LLM - Ko-EQ-Bench | 32.17 | EQ-Bench score | 81.5 |
| Open Chinese LLM - C-Eval Semantic | 86.08 | Accuracy (%) | 78.7 |
| Open Chinese LLM - HellaSwag | 64.82 | Accuracy (%) | 78.1 |
| Open Portuguese LLM - ENEM | 70.47 | Accuracy (%) | 76.6 |
| Open Chinese LLM - ARC Challenge | 57.51 | Accuracy (%) | 75.3 |
| Open CoT - LSAT Logical Reasoning | 15.69 | CoT Gain (%) | 75.2 |
| Open Chinese LLM - CMMLU | 63.4 | Accuracy (%) | 74.3 |
| Open CoT - LogiQA 2 | 11.58 | CoT Gain (%) | 74 |
Interactive version: theaggregate.ai/model?slug=yi-1-5-9b-chat-16k · How It Works · Data refreshed daily, snapshot 2026-10-20.