SeaLLMs-v3-1.5B-Chat: benchmark results
Provider: Alibaba. Access: Open.
Aggregate Rating 1404 ± 26, rank #5884 of 10916 rated models, from 21 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| ThaiSafetyBench - Misinformation Harms | 13.24 | Attack Success Rate (%) | 87 |
| ThaiSafetyBench - Human-Chatbot Interaction Harms | 13.68 | Attack Success Rate (%) | 78.3 |
| ThaiSafetyBench - Thai Culture-Related Attacks | 17.09 | Attack Success Rate (%) | 73.9 |
| ThaiSafetyBench - Thai Socio-Cultural Harms | 29.96 | Attack Success Rate (%) | 69.6 |
| ThaiSafetyBench - Information Hazards | 2.2 | Attack Success Rate (%) | 67.4 |
| FilBench - Reading Comprehension | 56.85 | Category Score (%) | 54.1 |
| ThaiSafetyBench - General Prompt Attacks | 9.32 | Attack Success Rate (%) | 43.5 |
| ThaiSafetyBench - Malicious Uses | 14.65 | Attack Success Rate (%) | 39.1 |
| ThaiSafetyBench - Discrimination, Exclusion, Toxicity, Hateful, Offensive | 13.94 | Attack Success Rate (%) | 34.8 |
| SEA LLM Leaderboard - SeaExam - Thai (Public) | 44 | Public Accuracy (%) | 26.7 |
| SEA LLM Leaderboard - SeaExam - Indonesian (Private) | 50.1 | Private Accuracy (%) | 23.9 |
| SEA LLM Leaderboard - SeaExam - Vietnamese (Private) | 51.9 | Private Accuracy (%) | 22.2 |
Interactive version: theaggregate.ai/model?slug=seallms-v3-1-5b-chat · How It Works · Data refreshed daily, snapshot 2026-11-08.