Thai LLM NLU - xcopa_tha_seacrowd_qa: leaderboard
Metric: Accuracy (%). Source: huggingface.co. 70 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o (2024-05-13) | 96.6 |
| 2 | Qwen 2.5 72B Instruct | 96 |
| 3 | Claude 3.5 Sonnet (20240620) | 94.4 |
| 4 | QwQ 32B-Preview | 93.2 |
| 5 | Llama 3.1 70B Instruct | 92.6 |
| 6 | Llama 3.3 70B Instruct | 92.4 |
| 7 | Qwen 2.5 32B Instruct | 92.4 |
| 8 | GPT-4o Mini (2024-07-18) | 92.4 |
| 9 | Llama 3.1 Nemotron 70B Instruct | 92.4 |
| 10 | Llama 3.1 70B Cpt Sea Lionv3 Instruct | 92.4 |
| 11 | Sailor2-8B-Chat | 91.2 |
| 12 | Qwen 2 72B Instruct | 91 |
| 13 | DeepSeek R1 Distill Qwen 32B | 90.4 |
| 14 | Tsunami-1.0-14B-Instruct | 89.8 |
| 15 | Qwen 2.5 14B Instruct | 89.6 |
Interactive version: theaggregate.ai/benchmark?slug=thai-llm-nlu-xcopa-tha-seacrowd-qa · How It Works · Data refreshed daily, snapshot 2026-09-05.