SEA LLM Leaderboard - SeaExam - Thai (Public): leaderboard
Metric: Public Accuracy (%). Source: huggingface.co. 91 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro (Preview 03-25) | 92.9 |
| 2 | Claude 3.5 Sonnet (20241022) | 80.9 |
| 3 | Claude 3.7 Sonnet (20250219) | 80.9 |
| 4 | Gemini 2.0 Flash | 79 |
| 5 | GPT-4.1 | 78 |
| 6 | Gemini 1.5 Pro | 78 |
| 7 | DeepSeek V3 (0324) | 77.8 |
| 8 | GPT-4o (2024-08-06) | 77 |
| 9 | Qwen 2.5 72B | 76.3 |
| 10 | Llama 4 Maverick Instruct | 75.8 |
| 11 | Qwen 2.5 72B Instruct | 75.2 |
| 12 | Qwen 2 72B | 74.4 |
| 13 | Gemini 2.0 Flash Lite | 74.2 |
| 14 | GPT-4.1 Mini | 72.2 |
| 15 | Qwen 2 72B Instruct | 71.7 |
Interactive version: theaggregate.ai/benchmark?slug=sea-llm-leaderboard-seaexam-thai-public · How It Works · Data refreshed daily, snapshot 2026-09-19.