openthaigpt1.5-14B-instruct: benchmark results
Provider: Other.
Aggregate Rating 1544 ± 41, rank #1783 of 10916 rated models, from 27 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Thai LLM NLU - wisesight_thai_sentiment_seacrowd_text | 53.46 | Accuracy (%) | 94.2 |
| Thai LLM NLU - xnli.tha_seacrowd_pairs | 42.89 | Accuracy (%) | 89.9 |
| Thai LLM MC - m3exam_tha_seacrowd_qa | 62.41 | Accuracy (%) | 88.4 |
| Thai LLM - Reasoning | 6.7 | Rating (0-10) | 88 |
| Thai LLM MC - thaiexam_qa | 58.41 | Accuracy (%) | 82.6 |
| Thai LLM NLG - flores200_tha_Thai_eng_Latn_seacrowd_t2t (chrF++) | 59.52 | chrF++ | 82.1 |
| Thai LLM - Coding | 7.14 | Rating (0-10) | 80.3 |
| Thai LLM NLU - belebele_tha_thai_seacrowd_qa | 85.11 | Accuracy (%) | 76.8 |
| Thai LLM - STEM | 6.65 | Rating (0-10) | 74.6 |
| Thai LLM - Social Science | 7.8 | Rating (0-10) | 73.2 |
| Thai LLM - Extraction | 5.7 | Rating (0-10) | 71.8 |
| Thai LLM NLU - xcopa_tha_seacrowd_qa | 89.2 | Accuracy (%) | 71 |
Interactive version: theaggregate.ai/model?slug=openthaigpt1-5-14b-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.