Yi-34Bx2-MoE-60B-DPO: benchmark results
cloudyu's DPO-tuned version of their 2x34B Yi-based mixture-of-experts, Yi-34Bx2-MoE-60B. Provider: cloudyu. Released 2024-01-23. Access: Open.
Aggregate Rating 1521 ± 22, rank #714 of 1656 rated models, from 20 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 73.92 | Accuracy (%) (5-shot) | 98.9 |
| Open LLM Leaderboard v1 - MMLU | 77.36 | Accuracy (%) (5-shot) | 98.6 |
| Open Chinese LLM Leaderboard | 70.61 | Official Nonzero-Task Mean (%) | 95.9 |
| Open Chinese LLM - C-Eval Semantic | 90.57 | Accuracy (%) | 95.3 |
| Open Chinese LLM - ARC Challenge | 64.08 | Accuracy (%) | 95 |
| Open LLM Leaderboard v1 - WinoGrande | 84.77 | Accuracy (%) (5-shot) | 95 |
| Open Chinese LLM - WinoGrande | 70.64 | Accuracy (%) | 94.7 |
| Open Chinese LLM - HellaSwag | 69.68 | Accuracy (%) | 92.6 |
| Open Chinese LLM - CMMLU | 71.11 | Accuracy (%) | 90.8 |
| Open LLM Leaderboard v1 - ARC Challenge | 71.25 | Normalized accuracy (%) (25-shot) | 88.6 |
| Open LLM Leaderboard - MMLU-Pro | 46.77 | Score | 85.8 |
| Open Chinese LLM - GSM8K | 60.35 | Accuracy (%) | 85.2 |
Interactive version: theaggregate.ai/model?slug=yi-34bx2-moe-60b-dpo · How It Works · Data refreshed daily, snapshot 2026-10-20.