typhoon2-qwen2.5-7B-instruct: benchmark results
Provider: Other.
Aggregate Rating 1505 ± 43, rank #2268 of 10916 rated models, from 27 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Thai LLM - Knowledge III | 5.3 | Rating (0-10) | 91.5 |
| Thai LLM - STEM | 7.25 | Rating (0-10) | 90.1 |
| Thai LLM NLG - flores200_eng_Latn_tha_Thai_seacrowd_t2t (chrF++) | 54.29 | chrF++ | 89.6 |
| Thai LLM NLG - flores200_eng_Latn_tha_Thai_seacrowd_t2t (SacreBLEU) | 38.78 | SacreBLEU | 88.1 |
| Thai LLM NLG - flores200_eng_Latn_tha_Thai_seacrowd_t2t (BLEU) | 27.68 | BLEU | 86.6 |
| Thai LLM - Social Science | 8.4 | Rating (0-10) | 85.2 |
| Thai LLM - Math | 6.45 | Rating (0-10) | 79.6 |
| Thai LLM NLG - flores200_tha_Thai_eng_Latn_seacrowd_t2t (chrF++) | 58.82 | chrF++ | 71.6 |
| Thai LLM NLG - iapp_squad_seacrowd_qa (ROUGE2) | 43.07 | ROUGE2 | 71.6 |
| Thai LLM NLG - flores200_tha_Thai_eng_Latn_seacrowd_t2t (SacreBLEU) | 33.09 | SacreBLEU | 70.1 |
| Thai LLM NLG - iapp_squad_seacrowd_qa (ROUGE1) | 52.53 | ROUGE1 | 70.1 |
| Thai LLM NLG - iapp_squad_seacrowd_qa (ROUGEL) | 52.17 | ROUGEL | 70.1 |
Interactive version: theaggregate.ai/model?slug=typhoon2-qwen2-5-7b-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.