Yi-1.5-9B Chat: benchmark results
01.AI's Apache-2.0 9B chat model from the Yi-1.5 series (May 2024), continually pretrained on 500B extra tokens and tuned on 3M samples. Provider: 01.AI. Released 2024-05-13. Access: Open.
Aggregate Rating 1443 ± 8, rank #1031 of 1656 rated models, from 500 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LA Leaderboard - ParafrasesGL | 56.12 | Accuracy (%) | 97.1 |
| OpenCompass Reasoning - Abductive - English (CompassBench 2405) | 88 | Score (%) | 96.1 |
| LatamBoard - Spanish MGSM | 18.8 | Score (%) | 93.9 |
| LA Leaderboard - ClinTreatES | 64.88 | Semantic Answer Similarity (x100) | 92.5 |
| Mobile-MMLU | 72.7 | Overall Accuracy (%) | 90.5 |
| LA Leaderboard - MGSM Galician | 8.8 | Exact Match (%) | 88.5 |
| LA Leaderboard - PAWS Catalan | 68.05 | Accuracy (%) | 88.2 |
| LA Leaderboard - Spanish Law Exams | 39.5 | Accuracy (%) | 88.2 |
| Open Chinese LLM - GSM8K | 64.22 | Accuracy (%) | 88.2 |
| LatamBoard - Spanish Escola | 71.04 | Score (%) | 87.9 |
| LA Leaderboard - Belebele Catalan | 80.67 | Accuracy (%) | 86.8 |
| LatamBoard - Spanish PAWS | 63 | Score (%) | 86.4 |
Interactive version: theaggregate.ai/model?slug=yi-1-5-9b-chat · How It Works · Data refreshed daily, snapshot 2026-10-20.