Yi-1.5-6B: benchmark results
01.AI's Apache-2.0 6B base model (May 2024): Yi-6B continued-pretrained on 500B additional tokens for stronger coding, math, and reasoning. Provider: 01.AI. Released 2024-05-11. Access: Open.
Unified ELO 1398 ± 1, rank #1141 of 1392 rated models, from 57 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MuSR | 13.31 | Score | 73.4 |
| EuroEval Portuguese NLU - MultiWikiQA PT | 72.84 | Reading comprehension Score (%) | 72.6 |
| Open Chinese LLM - WinoGrande | 65.04 | Accuracy (%) | 70.8 |
| Open LLM Leaderboard - GPQA | 8.5 | Score | 70.7 |
| MERA - ruCodeEval | 21.77 | pass@1 (%) | 66 |
| Open Chinese LLM - CMMLU | 57.54 | Accuracy (%) | 64.7 |
| Open Chinese LLM - C-Eval Semantic | 72.2 | Accuracy (%) | 58.8 |
| EuroEval Dutch NLU - DBRD | 87.76 | Sentiment classification Score (%) | 54.3 |
| MERA - ruHumanEval | 13.54 | pass@1 (%) | 53.4 |
| EuroEval Portuguese NLU - SST-2 PT | 77.09 | Sentiment classification Score (%) | 51.1 |
| Open Chinese LLM - HellaSwag | 60.24 | Accuracy (%) | 50.4 |
| MERA - ruMultiAr | 30.08 | EM (%) | 46.9 |
Interactive version: theaggregate.ai/model?slug=yi-1-5-6b · How It Works · Data refreshed daily, snapshot 2026-09-05.