llama3.2-typhoon2-1B-instruct: benchmark results

Provider: Meta. Access: Open.

Unified ELO 1327 ± 28, rank #2363 of 2656 rated models, from 35 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Thai LLM NLG - iapp_squad_seacrowd_qa (ROUGE1)62.84ROUGE183.6
Thai LLM NLG - iapp_squad_seacrowd_qa (ROUGEL)62.53ROUGEL83.6
Thai LLM NLG - iapp_squad_seacrowd_qa (ROUGE2)48.41ROUGE282.1
Thai LLM NLG - xl_sum_tha_seacrowd_t2t (ROUGEL)18.69ROUGEL62.7
Thai LLM NLG - xl_sum_tha_seacrowd_t2t (ROUGE2)9.49ROUGE260.4
Thai LLM NLG - xl_sum_tha_seacrowd_t2t (ROUGE1)26.7ROUGE158.2
Thai LLM - Knowledge III3.8Rating (0-10)49.3
Thai LLM - Roleplay6.25Rating (0-10)40.8
Thai LLM NLG - flores200_eng_Latn_tha_Thai_seacrowd_t2t (BLEU)18.69BLEU35.8
Thai LLM NLG - flores200_eng_Latn_tha_Thai_seacrowd_t2t (SacreBLEU)26.48SacreBLEU32.8
Thai LLM NLG - flores200_tha_Thai_eng_Latn_seacrowd_t2t (BLEU)42.52BLEU32.8
Thai LLM NLG - flores200_tha_Thai_eng_Latn_seacrowd_t2t (SacreBLEU)25.08SacreBLEU32.8

Interactive version: theaggregate.ai/model?slug=llama3-2-typhoon2-1b-instruct · How It Works · Data refreshed daily, snapshot 2026-09-19.