PLLuM-8x7B-nc-chat: benchmark results

Provider: PLLuM. Access: Open.

Unified ELO 1475 ± 21, rank #1339 of 2656 rated models, from 19 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
LLMZSZL Leaderboard60.52Score84.7
PLCC - Art & Entertainment72Accuracy (%)72.1
PLCC - Culture & Tradition76Accuracy (%)63.3
PLCC - Vocabulary68Accuracy (%)61.9
MT-Bench PL - STEM8.9Judge Score (0-10)58.2
MT-Bench PL - Extraction8.4Judge Score (0-10)53.1
PLCC - Overall68.17Mean category accuracy (%)49.8
MT-Bench PL - Overall6.43Judge Score (0-10)44.9
PLCC - Geography73Accuracy (%)42.3
PLCC - History73Accuracy (%)41.6
MT-Bench PL - Reasoning4.95Judge Score (0-10)39.8
MT-Bench PL - Roleplay6.9Judge Score (0-10)39.8

Interactive version: theaggregate.ai/model?slug=pllum-8x7b-nc-chat · How It Works · Data refreshed daily, snapshot 2026-09-19.