Yi-1.5-9B: benchmark results
01.AI's Apache-2.0 9B Yi-1.5 base model (May 2024) with improved coding, math, reasoning, and instruction-following over the original Yi. Provider: 01.AI. Released 2024-05-13. Access: Open.
Aggregate Rating 1395 ± 10, rank #1241 of 1656 rated models, from 411 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LA Leaderboard - CatalanQA | 84.05 | F1 (%) | 98.5 |
| LA Leaderboard - XQuAD Catalan | 77.5 | F1 (%) | 98.5 |
| LA Leaderboard - XQuAD Spanish | 79.5 | F1 (%) | 98.5 |
| LA Leaderboard - PAWS Catalan | 70.5 | Accuracy (%) | 97.1 |
| LA Leaderboard - Summarization Galician | 7.35 | BLEU | 95.5 |
| Open LLM Leaderboard - GPQA | 37.92 | Score | 94.6 |
| Open LLM Leaderboard v1 - MMLU | 70.73 | Accuracy (%) (5-shot) | 94.3 |
| EuroEval English NLU - SQuAD | 86.89 | Character F1 (%) | 92.6 |
| LA Leaderboard - XL-Sum Spanish | 3.26 | BLEU | 92.5 |
| EuroEval English NLU - SST-5 | 69.2 | Matthews correlation coefficient (%) | 92.4 |
| LA Leaderboard - MGSM Catalan | 12.4 | Exact Match (%) | 92.3 |
| EuroEval German NLU - Germanquad | 66.85 | Character F1 (%) | 92.2 |
Interactive version: theaggregate.ai/model?slug=yi-1-5-9b · How It Works · Data refreshed daily, snapshot 2026-10-20.