speechless-code-mistral-7B-v1.0 Benchmark Results

speechless-code-mistral-7B-v1.0 — benchmark results

Provider: Other. Released 2023-10-10. Access: Open.

Unified ELO 1364 ± 16, rank #1364 of 1776 rated models, from 15 benchmark results.

Benchmark	Score	Metric	Percentile
Open LLM Leaderboard - MuSR	14.77	Score	80.1
Open LLM Leaderboard - MMLU-Pro	23.84	Score	42
Open LLM Leaderboard - GPQA	4.59	Score	39.4
EvalPlus (HumanEval+ & MBPP+)	45.1	Pass@1 avg (%)	38.7
Open LLM Leaderboard - BBH	24.09	Score	36.7
Open LLM Leaderboard - IFEval	36.65	Score	35.2
Open LLM Leaderboard - MATH Level 5	5.21	Score	29.1
Open Chinese LLM - TruthfulQA MC	51.48	Accuracy (%)	28.6
Open Chinese LLM - CMMLU	47.85	Accuracy (%)	27.6
Open Chinese LLM - WinoGrande	61.17	Accuracy (%)	23.4
Open Chinese LLM - GSM8K	27.37	Accuracy (%)	19.7
Open Chinese LLM - ARC Challenge	45.99	Accuracy (%)	19.4