suzume-llama-3-8B-multilingual-orpo-borda-full Benchmark Results

suzume-llama-3-8B-multilingual-orpo-borda-full — benchmark results

Provider: Lightblue. Released 2024-04-25. Access: Open.

Unified ELO 1362 ± 23, rank #1373 of 1776 rated models, from 15 benchmark results.

Benchmark	Score	Metric	Percentile
Open Korean LLM Leaderboard	413.04	Average Score (%)	78.6
Open LLM Leaderboard - IFEval	58.17	Score	70
Open Chinese LLM - WinoGrande	63.93	Accuracy (%)	62.6
Open Chinese LLM - HellaSwag	60.66	Accuracy (%)	55.6
Open LLM Leaderboard - MMLU-Pro	25.66	Score	46.4
Open Chinese LLM - C-Eval Semantic	66.16	Accuracy (%)	40.1
Open LLM Leaderboard - MATH Level 5	7.63	Score	39.6
Open Chinese LLM - ARC Challenge	49.49	Accuracy (%)	39.2
Open LLM Leaderboard - BBH	25.08	Score	38.3
Open Chinese LLM - CMMLU	51.04	Accuracy (%)	37.7
Open Chinese LLM - TruthfulQA MC	52.17	Accuracy (%)	35
Open Chinese LLM Leaderboard	53.65	Average Score (%)	31.5