Yi-1.5-34B-Chat-16K: benchmark results
16K-context variant of 01.AI's Yi-1.5-34B-Chat, extending the standard 4K chat model for longer documents and conversations (May 2024). Provider: 01.AI. Released 2024-05-15. Access: Open.
Aggregate Rating 1485 ± 19, rank #824 of 1656 rated models, from 70 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 78 | Accuracy (%) (5-shot) | 99.1 |
| Open Chinese LLM - ARC Challenge | 63.74 | Accuracy (%) | 93.9 |
| Open Chinese LLM - C-Eval Semantic | 90.1 | Accuracy (%) | 93.2 |
| Open Chinese LLM - HellaSwag | 69.35 | Accuracy (%) | 91.4 |
| Open Chinese LLM - GSM8K | 66.72 | Accuracy (%) | 90.8 |
| Open Chinese LLM - WinoGrande | 69.53 | Accuracy (%) | 90.5 |
| Open LLM Leaderboard v1 - WinoGrande | 83.27 | Accuracy (%) (5-shot) | 87.9 |
| Open Portuguese LLM - FaQuAD NLI | 79.1 | Macro F1 (%) | 86.3 |
| Open Chinese LLM Leaderboard | 66.91 | Official Nonzero-Task Mean (%) | 85.2 |
| Open Chinese LLM - CMMLU | 70.03 | Accuracy (%) | 84.9 |
| Open LLM Leaderboard v1 - GSM8K | 67.93 | Accuracy (%) (5-shot) | 84.7 |
| Open LLM Leaderboard - MMLU-Pro | 45.45 | Score | 84.5 |
Interactive version: theaggregate.ai/model?slug=yi-1-5-34b-chat-16k · How It Works · Data refreshed daily, snapshot 2026-10-20.