CognitiveFusion2-4x7B-BF16 Benchmark Results

CognitiveFusion2-4x7B-BF16 — benchmark results

Provider: Other. Released 2024-04-06. Access: Open.

Unified ELO 1401 ± 15, rank #1223 of 1776 rated models, from 14 benchmark results.

Benchmark	Score	Metric	Percentile
Open Chinese LLM - TruthfulQA MC	63.93	Accuracy (%)	95.8
Open Chinese LLM - HellaSwag	60.98	Accuracy (%)	60.7
Open Chinese LLM - ARC Challenge	53.92	Accuracy (%)	60.5
Open Chinese LLM - GSM8K	47.23	Accuracy (%)	56.1
Open Chinese LLM Leaderboard	56.87	Average Score (%)	55.5
Open Chinese LLM - WinoGrande	63.14	Accuracy (%)	53.6
Open LLM Leaderboard - MuSR	9.95	Score	49.3
Open LLM Leaderboard - GPQA	4.81	Score	41
Open LLM Leaderboard - IFEval	35.67	Score	34.1
Open LLM Leaderboard - MATH Level 5	5.74	Score	31.8
Open LLM Leaderboard - MMLU-Pro	19.92	Score	30.8
Open Chinese LLM - C-Eval Semantic	62.26	Accuracy (%)	28.6