Sailor-1.8B: benchmark results
Provider: Sea AI Lab. Access: Open.
Unified ELO 1253 ± 19, rank #2799 of 2928 rated models, from 14 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 2.73 | Accuracy (%) (5-shot) | 20.7 |
| Open LLM Leaderboard v1 - MMLU | 30.44 | Accuracy (%) (5-shot) | 16.9 |
| Open LLM Leaderboard v1 - HellaSwag | 57.06 | Normalized accuracy (%) (10-shot) | 12.9 |
| Open LLM Leaderboard v1 - WinoGrande | 58.41 | Accuracy (%) (5-shot) | 11.5 |
| Open LLM Leaderboard v1 - ARC Challenge | 33.11 | Normalized accuracy (%) (25-shot) | 11.3 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 37.81 | MC2 (%) (0-shot) | 6.6 |
| SEA LLM Leaderboard - SeaExam - Thai (Private) | 26.8 | Private Accuracy (%) | 4.4 |
| SEA LLM Leaderboard - SeaExam - Vietnamese (Private) | 28.9 | Private Accuracy (%) | 3.3 |
| SEA LLM Leaderboard - SeaExam - Vietnamese (Public) | 27.4 | Public Accuracy (%) | 2.2 |
| SEA LLM Leaderboard - SeaExam | 26.3 | Private Average Score (%) | 1.7 |
| SEA LLM Leaderboard - SeaExam - Thai (Public) | 26.2 | Public Accuracy (%) | 1.7 |
| SEA LLM Leaderboard - SeaExam (Public) | 26.1 | Public Average Score (%) | 1.1 |
Interactive version: theaggregate.ai/model?slug=sailor-1-8b · How It Works · Data refreshed daily, snapshot 2026-09-23.