autotrain-llama3-70B-orpo-v1 Benchmark Results

autotrain-llama3-70B-orpo-v1 — benchmark results

Provider: Other. Access: Open.

Unified ELO 1369 ± 55, rank #1350 of 1776 rated models, from 14 benchmark results.

Benchmark	Score	Metric	Percentile
Open Chinese LLM - CMMLU	72.42	Accuracy (%)	96.4
Open Chinese LLM - GSM8K	68.84	Accuracy (%)	93.2
Open Chinese LLM Leaderboard	66.82	Average Score (%)	86.1
Open Chinese LLM - C-Eval Semantic	87.33	Accuracy (%)	84.3
Open Chinese LLM - ARC Challenge	58.96	Accuracy (%)	82.2
Open LLM Leaderboard - BBH	41.57	Score	80.8
Open Chinese LLM - HellaSwag	63.66	Accuracy (%)	73.9
Open Chinese LLM - TruthfulQA MC	54.11	Accuracy (%)	54.9
Open LLM Leaderboard - IFEval	42.33	Score	43.7
Open Chinese LLM - WinoGrande	62.43	Accuracy (%)	43.3
Open LLM Leaderboard - MuSR	2.57	Score	11.7
Open LLM Leaderboard - MATH Level 5	1.06	Score	7.6