Sailor-1.8B-Chat: benchmark results
Provider: Sea AI Lab. Access: Open.
Unified ELO 1295 ± 20, rank #2712 of 2928 rated models, from 14 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 3.56 | Accuracy (%) (5-shot) | 21.7 |
| Open LLM Leaderboard v1 - MMLU | 38.31 | Accuracy (%) (5-shot) | 20.1 |
| SEA LLM Leaderboard - SeaExam - Thai (Private) | 33.6 | Private Accuracy (%) | 14.4 |
| Open LLM Leaderboard v1 - ARC Challenge | 35.75 | Normalized accuracy (%) (25-shot) | 13.3 |
| Open LLM Leaderboard v1 - HellaSwag | 57.12 | Normalized accuracy (%) (10-shot) | 12.9 |
| Open LLM Leaderboard v1 - WinoGrande | 59.12 | Accuracy (%) (5-shot) | 12.3 |
| SEA LLM Leaderboard - SeaExam - Indonesian (Public) | 35.2 | Public Accuracy (%) | 10 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 38.71 | MC2 (%) (0-shot) | 8.8 |
| SEA LLM Leaderboard - SeaExam (Public) | 35 | Public Average Score (%) | 7.8 |
| SEA LLM Leaderboard - SeaExam - Vietnamese (Private) | 40.9 | Private Accuracy (%) | 7.8 |
| SEA LLM Leaderboard - SeaExam - Vietnamese (Public) | 39.2 | Public Accuracy (%) | 7.8 |
| SEA LLM Leaderboard - SeaExam | 36.2 | Private Average Score (%) | 6.7 |
Interactive version: theaggregate.ai/model?slug=sailor-1-8b-chat · How It Works · Data refreshed daily, snapshot 2026-09-23.