Qwen2.5-14B-Gutenberg-Instruct-Slerpeno Benchmark Results

Qwen2.5-14B-Gutenberg-Instruct-Slerpeno: benchmark results

Community SLERP merge of Qwen 2.5 14B fine-tunes (Gutenberg). Provider: v000000. Released 2024-09-20. Access: Open.

Aggregate Rating 1606 ± 21, rank #421 of 1654 rated models, from 20 benchmark results.

Benchmark	Score	Metric	Percentile
Open Korean LLM - Ko-IFEval	68.42	Strict accuracy, prompt/instruction mean (%)	99.7
Open Korean LLM Leaderboard	54.53	Average Score (%)	99.7
Open Korean LLM - Ko-GSM8K (flexible extract)	76.35	Exact match, flexible extract (%)	99.4
Open Korean LLM - KorNAT-CKA	39.85	Normalized accuracy (%)	99
Open LLM Leaderboard - IFEval	81.97	Score	98.8
Open Portuguese LLM - ASSIN2 RTE	94.73	Macro F1 (%)	98.6
Open LLM Leaderboard - MATH Level 5	53.25	Score	98.4
Open Korean LLM - Ko-EQ-Bench	58.84	EQ-Bench score	98.2
Open Korean LLM - KorNAT-Helpful	60.05	Normalized accuracy (%)	97.7
Open Korean LLM - Ko-Winogrande	69.85	Accuracy (%)	95.8
Open Korean LLM - KorNAT-Harmless	72.59	Normalized accuracy (%)	95.6
Open Korean LLM - Ko-GPQA-Diamond	27.78	Normalized accuracy (%)	95