speechless-zephyr-code-functionary-7B Benchmark Results

speechless-zephyr-code-functionary-7B — benchmark results

Provider: Other. Released 2024-01-23. Access: Open.

Unified ELO 1359 ± 19, rank #1387 of 1776 rated models, from 14 benchmark results.

Benchmark	Score	Metric	Percentile
Open LLM Leaderboard - MuSR	11.61	Score	61.9
Open LLM Leaderboard - GPQA	6.71	Score	56.5
Open LLM Leaderboard - BBH	25.98	Score	40.2
Open LLM Leaderboard - MMLU-Pro	23.27	Score	39.7
Open Chinese LLM - CMMLU	48.74	Accuracy (%)	30
Open LLM Leaderboard - MATH Level 5	4.23	Score	24.2
Open LLM Leaderboard - IFEval	26.96	Score	24
Open Chinese LLM - WinoGrande	61.01	Accuracy (%)	21.8
Open Chinese LLM - GSM8K	27.67	Accuracy (%)	20.5
Open Chinese LLM - HellaSwag	54.25	Accuracy (%)	19.9
Open Chinese LLM - TruthfulQA MC	50.06	Accuracy (%)	19.3
Open Chinese LLM - ARC Challenge	45.9	Accuracy (%)	18.7