tongyi-model-v1.0-1B: benchmark results

Provider: Other.

Aggregate Rating 1280 ± 43, rank #8870 of 10556 rated models, from 27 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Thai LLM NLU - xnli.tha_seacrowd_pairs33.33Accuracy (%)26.1
Thai LLM NLG - xl_sum_tha_seacrowd_t2t (ROUGE2)7.49ROUGE220.9
Thai LLM NLU - belebele_tha_thai_seacrowd_qa48.56Accuracy (%)18.8
Thai LLM NLG - xl_sum_tha_seacrowd_t2t (ROUGE1)20.09ROUGE117.9
Thai LLM NLG - xl_sum_tha_seacrowd_t2t (ROUGEL)13.87ROUGEL17.9
Thai LLM MC - m3exam_tha_seacrowd_qa28.51Accuracy (%)14.5
Thai LLM NLU - wisesight_thai_sentiment_seacrowd_text32.76Accuracy (%)14.5
Thai LLM - Coding2.95Rating (0-10)13.4
Thai LLM NLG - flores200_tha_Thai_eng_Latn_seacrowd_t2t (BLEU)19.9BLEU13.4
Thai LLM NLG - flores200_tha_Thai_eng_Latn_seacrowd_t2t (chrF++)28.24chrF++13.4
Thai LLM NLG - flores200_tha_Thai_eng_Latn_seacrowd_t2t (SacreBLEU)8.32SacreBLEU11.9
Thai LLM NLU - xcopa_tha_seacrowd_qa52.8Accuracy (%)11.6

Interactive version: theaggregate.ai/model?slug=tongyi-model-v1-0-1b · How It Works · Data refreshed daily, snapshot 2026-11-17.