dolphin-2.9.1-mixtral-1x22B Benchmark Results

dolphin-2.9.1-mixtral-1x22B — benchmark results

Provider: Cognitive Computations. Released 2024-05-22. Access: Open.

Unified ELO 1239 ± 30, rank #1644 of 1776 rated models, from 9 benchmark results.

Benchmark	Score	Metric	Percentile
Open Chinese LLM - TruthfulQA MC	52.87	Accuracy (%)	42.9
Open Chinese LLM - GSM8K	9.4	Accuracy (%)	8.5
Open Korean LLM Leaderboard	28.95	Average Score (%)	7.5
Open Chinese LLM - ARC Challenge	37.12	Accuracy (%)	4.7
Open Chinese LLM Leaderboard	34.95	Average Score (%)	3.6
Open Chinese LLM - C-Eval Semantic	31.39	Accuracy (%)	3
Open Chinese LLM - CMMLU	30.77	Accuracy (%)	2.7
Open Chinese LLM - HellaSwag	31.97	Accuracy (%)	2.1
Open Chinese LLM - WinoGrande	51.14	Accuracy (%)	2.1