Yi-34Bx2-MoE-60B-DPO Benchmark Results

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: 01.AI. Released 2024-01-23. Access: Open.

Unified ELO 1490 ± 17, rank #840 of 1776 rated models, from 14 benchmark results.

Benchmark	Score	Metric	Percentile
Open Chinese LLM Leaderboard	69.46	Average Score (%)	96.1
Open Chinese LLM - C-Eval Semantic	90.57	Accuracy (%)	95.3
Open Chinese LLM - ARC Challenge	64.08	Accuracy (%)	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 - MMLU-Pro	40.85	Score	85.7
Open Chinese LLM - GSM8K	60.35	Accuracy (%)	85.2
Open Chinese LLM - TruthfulQA MC	59.79	Accuracy (%)	82.5
Open LLM Leaderboard - MuSR	14.32	Score	78.3
Open LLM Leaderboard - GPQA	9.62	Score	76.6
Open LLM Leaderboard - IFEval	53.19	Score	63.3

Interactive version: theaggregate.ai/model?slug=yi-34bx2-moe-60b-dpo · How the rankings work · Data refreshed daily, snapshot 2026-07-22.