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
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Ru Arena Hard | 93.46 | Win Rate (%) | 98.5 |
| K-12EduBench | 69.87 | Lambda_js Avg (self-reported) | 63.6 |
| LLM2014 Logic 2024-10 | 50.68 | Score (%) | 51.9 |
| AI for Education Pedagogy - Science | 77.6 | Accuracy (%) | 48.6 |
| BenchTable | 45.6 | Total Score (%) | 44.3 |
| Chatbot Arena (Text) | 1328 | Elo | 44.1 |
| AI for Education Pedagogy - Social studies | 72.73 | Accuracy (%) | 43.2 |
| LLM2014 Logic 2024-12 | 48.81 | Score (%) | 37.9 |
| LLM2014 Logic 2025-01 | 35.47 | Score (%) | 35.7 |
| AI for Education Pedagogy - Maths | 69.05 | Accuracy (%) | 33 |
| AI for Education Pedagogy | 71.75 | Accuracy (%) | 32.7 |
| AI for Education Pedagogy - Secondary | 70.75 | Accuracy (%) | 32.3 |
Interactive version: theaggregate.ai/model?slug=yi-lightning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.