Dolphin3.0-R1-Mistral-24B Benchmark Results

Dolphin3.0-R1-Mistral-24B — benchmark results

Provider: Cognitive Computations. Released 2025-02-06. Access: Open.

Unified ELO 1379 ± 10, rank #1316 of 1776 rated models, from 179 benchmark results.

Benchmark	Score	Metric	Percentile
Open LLM Leaderboard - MATH Level 5	31.19	Score	82.6
Open LLM Leaderboard - BBH	33.76	Score	66.3
Open Arabic LLM - Arabic MMLU HT Abstract Algebra	29	Accuracy (%)	54.9
Open Arabic LLM - Arabic MMLU LAW (Professional)	63.38	Accuracy (%)	50.9
Open LLM Leaderboard - GPQA	5.93	Score	49.7
Open Japanese LLM - CG	7.83	Score (%)	47.8
Open Japanese LLM - Jamp Exact Match	58.33	Score (%)	43.5
Open Arabic LLM - Alghafa Multiple Choice Grounded Statement Xglue Mlqa Task	70.67	Accuracy (%)	42
Open Japanese LLM - Mbpp Pylint Check	13.05	Score (%)	41.3
Open LLM Leaderboard - IFEval	40.68	Score	40.8
Open Japanese LLM - Wiki NER SET F1	3.54	Score (%)	39.4
Open Arabic LLM - Alghafa Multiple Choice Grounded Statement Soqal Task	70	Accuracy (%)	38