Yi Large: benchmark results
01.AI's closed API flagship chat model with strong multilingual performance, the Chinese startup's top proprietary offering of 2024. Provider: 01.AI. Released 2024-06-25. Access: API.
Aggregate Rating 1564 ± 12, rank #565 of 1656 rated models, from 218 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenCompass Math - Primary School - English (CompassBench 2405) | 89.3 | Score (%) | 97.4 |
| OpenCompass Agent - T-Eval - Chinese (CompassBench 2407) | 85.6 | Score (%) | 97.1 |
| OpenCompass LLM - Agent (CompassBench 2407) | 86.1 | Score (%) | 97.1 |
| OpenCompass Agent - T-Eval - Chinese (CompassBench 2409) | 85.8 | Score (%) | 96.6 |
| OpenCompass LLM - Reasoning - English (CompassBench 2405) | 45.9 | Score (%) | 94.7 |
| OpenCompass Code - MBPP - English (CompassBench 2405) | 79 | Score (%) | 94.6 |
| OpenCompass LLM - Agent (CompassBench 2409) | 86.2 | Score (%) | 93.1 |
| OpenCompass Code - LCBench - Chinese (CompassBench 2405) | 51.5 | Score (%) | 92.1 |
| OpenCompass Code - LCBench - English (CompassBench 2405) | 49.8 | Score (%) | 92.1 |
| OpenCompass LLM - Agent (CompassBench 2405) | 76.2 | Score (%) | 92.1 |
| OpenCompass LLM - Code - Chinese (CompassBench 2405) | 59.7 | Score (%) | 92.1 |
| OpenCompass LLM - Knowledge (CompassBench 2405) | 71.1 | Score (%) | 92.1 |
Interactive version: theaggregate.ai/model?slug=yi-large · How It Works · Data refreshed daily, snapshot 2026-10-20.