Pathumma-llm-text-1.0.0: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1447 ± 43, rank #4013 of 10556 rated models, from 27 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Thai LLM NLG - flores200_tha_Thai_eng_Latn_seacrowd_t2t (BLEU) | 52.77 | BLEU | 94 |
| Thai LLM NLG - flores200_tha_Thai_eng_Latn_seacrowd_t2t (SacreBLEU) | 36.09 | SacreBLEU | 88.1 |
| Thai LLM NLG - flores200_tha_Thai_eng_Latn_seacrowd_t2t (chrF++) | 59.68 | chrF++ | 83.6 |
| Thai LLM NLU - xnli.tha_seacrowd_pairs | 40.4 | Accuracy (%) | 78.3 |
| Thai LLM NLG - flores200_eng_Latn_tha_Thai_seacrowd_t2t (BLEU) | 26.66 | BLEU | 77.6 |
| Thai LLM NLG - flores200_eng_Latn_tha_Thai_seacrowd_t2t (SacreBLEU) | 36.95 | SacreBLEU | 76.1 |
| Thai LLM NLG - flores200_eng_Latn_tha_Thai_seacrowd_t2t (chrF++) | 52.98 | chrF++ | 76.1 |
| Thai LLM MC - m3exam_tha_seacrowd_qa | 54.89 | Accuracy (%) | 68.1 |
| Thai LLM NLG - xl_sum_tha_seacrowd_t2t (ROUGE2) | 9.67 | ROUGE2 | 64.2 |
| Thai LLM - Knowledge III | 4.05 | Rating (0-10) | 64.1 |
| Thai LLM NLG - iapp_squad_seacrowd_qa (ROUGE2) | 34.61 | ROUGE2 | 62.7 |
| Thai LLM NLG - iapp_squad_seacrowd_qa (ROUGE1) | 42.75 | ROUGE1 | 61.2 |
Interactive version: theaggregate.ai/model?slug=pathumma-llm-text-1-0-0 · How It Works · Data refreshed daily, snapshot 2026-11-17.