Qwen2.5-32B-Instruct-abliterated Benchmark Results

Qwen2.5-32B-Instruct-abliterated: benchmark results

Provider: Alibaba. Released 2024-09-29. Access: Open.

Unified ELO 1667 ± 30, rank #408 of 2656 rated models, from 132 benchmark results.

Benchmark	Score	Metric	Percentile
Open Portuguese LLM - BLUEX	78.58	Accuracy (%)	97.8
Open Portuguese LLM - ASSIN2 RTE	94.48	Macro F1 (%)	96.8
Open Portuguese LLM - ENEM	83.41	Accuracy (%)	96.7
Open Arabic LLM - Arabic MMLU HT High School Computer Science	83	Accuracy (%)	95.4
Open Portuguese LLM - OAB Exams	62.78	Accuracy (%)	95.2
Open Arabic LLM - Arabic MMLU HT Virology	52.41	Accuracy (%)	93.8
Open Arabic LLM - Alghafa Multiple Choice Grounded Statement Soqal Task	94	Accuracy (%)	93.5
Open Arabic LLM - Alghafa Multiple Choice Rating Sentiment Task	55.56	Accuracy (%)	92
Open Arabic LLM - Arabic MMLU Math (Primary School)	78.48	Accuracy (%)	92
Open Arabic LLM - Arabic MMLU HT Abstract Algebra	47	Accuracy (%)	91.4
Open Arabic LLM - Arabic MMLU History (Primary School)	71.57	Accuracy (%)	90.4
Open Arabic LLM - Aratrust Privacy	96.49	Accuracy (%)	90.4