Nous-Hermes-2-SOLAR-10.7B Benchmark Results

Nous-Hermes-2-SOLAR-10.7B — benchmark results

Provider: Nous Research. Released 2024-01-01. Access: Open.

Unified ELO 1400 ± 12, rank #1225 of 1776 rated models, from 20 benchmark results.

Benchmark	Score	Metric	Percentile
Open LLM Leaderboard - MuSR	13.83	Score	76.1
Open Korean LLM Leaderboard	376.54	Average Score (%)	74
Open PL LLM - Multiple Choice	53.08	Average Multiple-Choice Score (%)	72.4
Open PL LLM Leaderboard	56.09	Average Score (%)	71.3
Open PL LLM - RAG	67.78	Average RAG Score (%)	71
Open LLM Leaderboard - BBH	34.99	Score	70.4
Open Chinese LLM - TruthfulQA MC	56.42	Accuracy (%)	70.3
Open PL LLM - Generative	58.41	Average Generative Score (%)	67.1
Open LLM Leaderboard - IFEval	52.79	Score	62.8
Open LLM Leaderboard - MMLU-Pro	27.31	Score	50.2
Open LLM Leaderboard - GPQA	5.82	Score	48.6
Polish EQ-Bench	49.85	EQ-Bench Score	43.6