llama-3-typhoon-v1.5-8B-instruct: benchmark results

Provider: Meta. Access: Open.

Unified ELO 1441 ± 1, rank #984 of 1392 rated models, from 35 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Thai LLM NLG - xl_sum_tha_seacrowd_t2t (ROUGE1)29.71ROUGE179.1
Thai LLM NLG - xl_sum_tha_seacrowd_t2t (ROUGE2)10.4ROUGE277.6
Thai LLM NLG - iapp_squad_seacrowd_qa (ROUGE1)56.66ROUGE176.1
Thai LLM NLG - iapp_squad_seacrowd_qa (ROUGE2)44.22ROUGE276.1
Thai LLM NLG - iapp_squad_seacrowd_qa (ROUGEL)55.99ROUGEL76.1
Thai LLM NLG - xl_sum_tha_seacrowd_t2t (ROUGEL)19.73ROUGEL74.6
Thai LLM - Writing6.6Rating (0-10)63.4
Thai LLM - STEM6.05Rating (0-10)56.3
Thai LLM - Reasoning4.8Rating (0-10)54.9
Open Chinese LLM - TruthfulQA MC53.41Accuracy (%)47.8
Thai LLM - Knowledge III3.7Rating (0-10)46.5
Thai LLM NLU - wisesight_thai_sentiment_seacrowd_text41.3Accuracy (%)44.9

Interactive version: theaggregate.ai/model?slug=llama-3-typhoon-v1-5-8b-instruct · How It Works · Data refreshed daily, snapshot 2026-09-05.