OrionStar-Yi-34B-Chat: benchmark results

Provider: Other. Access: Open.

Unified ELO 1523 ± 33, rank #965 of 2656 rated models, from 77 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
OpenCompass Knowledge - Common Sense - Chinese (CompassBench 2404)77.6Score (%)100
OpenCompass Knowledge - Humanities - Chinese (CompassBench 2404)56.9Score (%)96.7
OpenCompass LLM - Language - Chinese (CompassBench 2404)61.8Score (%)96.7
OpenCompass Language - Intention Recognition - Chinese (CompassBench 2404)70.3Score (%)96.7
OpenCompass Language - Traditional Cultural Understanding - Chinese (CompassBench 2404)65.3Score (%)95
OpenCompass LLM - Knowledge - Chinese (CompassBench 2404)63.8Score (%)93.3
OpenCompass Language - Chinese Semantic Understanding - Chinese (CompassBench 2404)71Score (%)93.3
OpenCompass Language - Sentiment Analysis - English (CompassBench 2404)77Score (%)93.3
OpenCompass Reasoning - Common Sense - Chinese (CompassBench 2404)47.1Score (%)93.3
OpenCompass LLM - Knowledge (CompassBench 2404)69.4Score (%)91.7
OpenCompass Knowledge - Social Science - Chinese (CompassBench 2404)68.8Score (%)90
OpenCompass LLM - Language (CompassBench 2404)58.1Score (%)90

Interactive version: theaggregate.ai/model?slug=orionstar-yi-34b-chat · How It Works · Data refreshed daily, snapshot 2026-09-19.