lambda-qwen2.5-32B-dpo-test Benchmark Results

lambda-qwen2.5-32B-dpo-test — benchmark results

tanliboy's experimental DPO fine-tune of Qwen 2.5 32B Instruct. Provider: Other. Released 2024-09-22. Access: Open.

Unified ELO 1595 ± 10, rank #485 of 1776 rated models, from 129 benchmark results.

Benchmark	Score	Metric	Percentile
Open Arabic LLM - Arabic MMLU Philosophy (High School)	76.92	Accuracy (%)	100
Open LLM Leaderboard - MATH Level 5	61.03	Score	99.8
Open Arabic LLM - Arabic MMLU Computer Science (University)	82.81	Accuracy (%)	99.7
Open LLM Leaderboard - MMLU-Pro	51.74	Score	98.9
Open Arabic LLM - Alghafa Meta AR MSA	92.07	Accuracy (%)	98.8
Open Arabic LLM - Alghafa Multiple Choice Grounded Statement Soqal Task	95.33	Accuracy (%)	98.8
Open LLM Leaderboard - IFEval	80.84	Score	98.2
Open Arabic LLM - Arabic MMLU HT Moral Scenarios	57.88	Accuracy (%)	97.5
Open LLM Leaderboard - BBH	54.41	Score	96.5
Open Arabic LLM - Arabic MMLU Economics (High School)	73.61	Accuracy (%)	95.1
Open Arabic LLM - Arabic MMLU HT Elementary Mathematics	69.84	Accuracy (%)	95.1
Open Arabic LLM - Arabic MMLU Arabic Language (High School)	46.67	Accuracy (%)	94.1