Sailor2-1B-Chat: benchmark results
Provider: Sea AI Lab. Access: Open.
Unified ELO 1273 ± 24, rank #1493 of 1632 rated models, from 85 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Thai LLM - Writing | 5.55 | Rating (0-10) | 33.1 |
| Thai LLM - Roleplay | 5.8 | Rating (0-10) | 31.7 |
| Open Japanese LLM - Xlsum JA Rouge1 | 20.81 | Score (%) | 29.6 |
| Open Japanese LLM - Xlsum JA Bert Score JA F1 | 67.11 | Score (%) | 27.9 |
| Open Japanese LLM - Xlsum JA RougeLsum | 17.05 | Score (%) | 26 |
| Thai LLM NLU - wisesight_thai_sentiment_seacrowd_text | 33.81 | Accuracy (%) | 18.8 |
| Thai LLM NLG - flores200_tha_Thai_eng_Latn_seacrowd_t2t (chrF++) | 41.39 | chrF++ | 17.9 |
| Open Japanese LLM - SUM | 5.67 | Score (%) | 17.8 |
| Open Japanese LLM - Xlsum JA Rouge2 | 5.69 | Score (%) | 17.8 |
| Thai LLM - STEM | 3.6 | Rating (0-10) | 17.6 |
| Thai LLM MC - m3exam_tha_seacrowd_qa | 30.12 | Accuracy (%) | 17.4 |
| Thai LLM MC - thaiexam_qa | 30.62 | Accuracy (%) | 17.4 |
Interactive version: theaggregate.ai/model?slug=sailor2-1b-chat · How It Works · Data refreshed daily, snapshot 2026-10-08.