Yi Lightning — benchmark results

01.AI's fast proprietary MoE flagship, API-only, which debuted in the Chatbot Arena top 10 at launch (October 2024). Provider: 01.AI. Released 2024-10-16. Access: API.

Unified ELO 1551 ± 46, rank #617 of 1776 rated models, from 16 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Ru Arena Hard93.46Win Rate (%)98.5
K-12EduBench69.87Lambda_js Avg (self-reported)63.6
LLM2014 Logic 2024-1050.68Score (%)51.9
AI for Education Pedagogy - Science77.6Accuracy (%)48.6
BenchTable45.6Total Score (%)44.3
Chatbot Arena (Text)1328Elo44.1
AI for Education Pedagogy - Social studies72.73Accuracy (%)43.2
LLM2014 Logic 2024-1248.81Score (%)37.9
LLM2014 Logic 2025-0135.47Score (%)35.7
AI for Education Pedagogy - Maths69.05Accuracy (%)33
AI for Education Pedagogy71.75Accuracy (%)32.7
AI for Education Pedagogy - Secondary70.75Accuracy (%)32.3

Interactive version: theaggregate.ai/model?slug=yi-lightning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.