Rombos-LLM-V2.5-Qwen-72B Benchmark Results

Rombos-LLM-V2.5-Qwen-72B — benchmark results

rombodawg's continuous fine-tune of Qwen 2.5 72B (instruct TIES-merged with base). Provider: Other. Released 2024-09-30. Access: Open.

Unified ELO 1637 ± 10, rank #395 of 1776 rated models, from 129 benchmark results.

Benchmark	Score	Metric	Percentile
Open LLM Leaderboard - MMLU-Pro	54.83	Score	99.8
Open LLM Leaderboard - BBH	61.27	Score	99.6
Open Arabic LLM - Alghafa Multiple Choice Sentiment Task	43.78	Accuracy (%)	99.4
Open Arabic LLM - Arabic MMLU Civics (High School)	58.62	Accuracy (%)	99.4
Open Arabic LLM - Arabic MMLU Computer Science (High School)	82.76	Accuracy (%)	99.4
Open Arabic LLM - Arabic MMLU HT Elementary Mathematics	71.69	Accuracy (%)	99.4
Open Arabic LLM - Arabic MMLU LAW (Professional)	80.89	Accuracy (%)	99.4
Open Arabic LLM - Alghafa Multiple Choice Grounded Statement Xglue Mlqa Task	94.67	Accuracy (%)	99.1
Open Arabic LLM - Arabic MMLU Economics (High School)	76.94	Accuracy (%)	99.1
Open LLM Leaderboard - GPQA	19.8	Score	99
Open LLM Leaderboard - MATH Level 5	54.23	Score	98.9
Open Arabic LLM - Alghafa Meta AR Dialects	84.71	Accuracy (%)	98.8