Yi-1.5-6B-Chat: benchmark results

Provider: 01.AI. Released 2024-05-11. Access: Open.

Unified ELO 1395 ± 1, rank #1157 of 1392 rated models, from 61 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard - MuSR14.03Score76.9
LatamBoard - Spanish PAWS61.5Score (%)72.7
Open LLM Leaderboard - MATH Level 516.24Score64.2
LatamBoard - Spanish MGSM9.6Score (%)63.6
Open LLM Leaderboard - IFEval51.45Score61.3
Open LLM Leaderboard - GPQA6.94Score58.3
Mobile-MMLU60.5Overall Accuracy (%)57.1
MAGI-Hard46.18Accuracy (%, 2024-05 snapshot)53.4
MERA - BPS95.7Accuracy (%)51.9
LatamBoard - Spanish Escola66.1Score (%)50
Open LLM Leaderboard - MMLU-Pro24.37Score43.6
MERA - RWSD54.62Accuracy (%)40.9

Interactive version: theaggregate.ai/model?slug=yi-1-5-6b-chat · How It Works · Data refreshed daily, snapshot 2026-09-05.