ConfigurableHermes-7B Benchmark Results

ConfigurableHermes-7B: benchmark results

Provider: Other. Released 2024-02-17. Access: Open.

Unified ELO 1418 ± 1, rank #1079 of 1392 rated models, from 15 benchmark results.

Benchmark	Score	Metric	Percentile
Open Chinese LLM - TruthfulQA MC	58.47	Accuracy (%)	76.9
Open LLM Leaderboard - IFEval	54.11	Score	64.9
Open Korean LLM Leaderboard	37.47	Average Score (%)	59.7
Open LLM Leaderboard - MuSR	9.11	Score	44
Open LLM Leaderboard - MMLU-Pro	22.5	Score	37.2
Open Chinese LLM - GSM8K	38.82	Accuracy (%)	36.9
Open LLM Leaderboard - BBH	23.16	Score	35.1
Open LLM Leaderboard - GPQA	3.58	Score	31.9
Open LLM Leaderboard - MATH Level 5	4.76	Score	26.9
Open Chinese LLM Leaderboard	51.53	Average Score (%)	23.7
Open Chinese LLM - C-Eval Semantic	58.12	Accuracy (%)	19.6
Open Chinese LLM - HellaSwag	54.17	Accuracy (%)	19.6

Interactive version: theaggregate.ai/model?slug=configurablehermes-7b · How It Works · Data refreshed daily, snapshot 2026-09-05.