Thai LLM - Roleplay: leaderboard
Metric: Rating (0-10). Source: huggingface.co. 72 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 1.5 Pro (001) | 8 |
| 2 | GPT-4o (2024-05-13) | 7.9 |
| 3 | Gemini 1.5 Flash (001) | 7.85 |
| 4 | GPT-4o Mini (2024-07-18) | 7.8 |
| 5 | Llama 3.1 Nemotron 70B Instruct | 7.75 |
| 6 | QwQ 32B-Preview | 7.7 |
| 7 | gemma2-9B-cpt-sea-lionv3-instruct | 7.7 |
| 8 | DeepSeek R1 Distill Qwen 32B | 7.65 |
| 9 | Qwen 2.5 14B Instruct | 7.65 |
| 10 | Qwen 2.5 32B Instruct | 7.6 |
| 11 | Qwen 2.5 72B Instruct | 7.55 |
| 12 | Gemma 2 9B (IT) | 7.5 |
| 13 | DeepSeek R1 Distill Llama 70B | 7.5 |
| 14 | Qwen 2 72B Instruct | 7.5 |
| 15 | Llama 3.1 8B Cpt Sea Lionv3 Instruct | 7.5 |
Interactive version: theaggregate.ai/benchmark?slug=thai-llm-roleplay · How It Works · Data refreshed daily, snapshot 2026-09-05.