Sailor-14B-Chat: benchmark results
Provider: Sea AI Lab. Access: Open.
Aggregate Rating 1464 ± 28, rank #3114 of 10916 rated models, from 22 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| HELM ThaiExam - A-Level | 41.73 | EM | 61 |
| HELM ThaiExam - ONET | 50 | EM | 61 |
| SEA LLM Leaderboard - SeaExam - Vietnamese (Private) | 68.4 | Private Accuracy (%) | 53.3 |
| SEA LLM Leaderboard - SeaExam - Thai (Public) | 57.1 | Public Accuracy (%) | 52.8 |
| SEA LLM Leaderboard - SeaExam (Public) | 58.2 | Public Average Score (%) | 50 |
| SEA LLM Leaderboard - SeaExam - Thai (Private) | 49.7 | Private Accuracy (%) | 50 |
| SEA LLM Leaderboard - SeaExam - Indonesian (Public) | 55.2 | Public Accuracy (%) | 49.4 |
| SEA LLM Leaderboard - SeaExam | 58.6 | Private Average Score (%) | 48.9 |
| SEA LLM Leaderboard - SeaExam - Vietnamese (Public) | 62.2 | Public Accuracy (%) | 48.9 |
| HELM ThaiExam - IC | 47.37 | EM | 48.8 |
| HELM ThaiExam - ThaiExam | 48.5 | EM | 48.8 |
| SEA LLM Leaderboard - SeaExam - Indonesian (Private) | 57.6 | Private Accuracy (%) | 44.4 |
Interactive version: theaggregate.ai/model?slug=sailor-14b-chat · How It Works · Data refreshed daily, snapshot 2026-11-08.