Thai LLM NLU - belebele_tha_thai_seacrowd_qa: leaderboard
Metric: Accuracy (%). Source: huggingface.co. 70 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude 3.5 Sonnet (20240620) | 90.22 |
| 2 | GPT-4o (2024-05-13) | 89.78 |
| 3 | Llama 3.1 Nemotron 70B Instruct | 88.33 |
| 4 | Qwen 2.5 32B Instruct | 88.22 |
| 5 | Qwen 2.5 72B Instruct | 87.67 |
| 6 | Llama 3.1 70B Instruct | 87.56 |
| 7 | Llama 3.1 70B Cpt Sea Lionv3 Instruct | 87.22 |
| 8 | Llama 3.3 70B Instruct | 86.67 |
| 9 | Qwen 2 72B Instruct | 86.11 |
| 10 | Qwen 2.5 14B Instruct | 85.44 |
| 11 | Tsunami-1.0-14B-Instruct | 85.33 |
| 12 | gemma2-9B-cpt-sea-lionv3-instruct | 85 |
| 13 | GPT-4o Mini (2024-07-18) | 84.78 |
| 14 | QwQ 32B-Preview | 84 |
| 15 | Gemma 2 9B (IT) | 83.78 |
Interactive version: theaggregate.ai/benchmark?slug=thai-llm-nlu-belebele-tha-thai-seacrowd-qa · How It Works · Data refreshed daily, snapshot 2026-09-05.