llama-3-typhoon-v1.5x-8B-instruct: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1460 ± 40, rank #3350 of 10916 rated models, from 27 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Thai LLM NLG - iapp_squad_seacrowd_qa (ROUGE1) | 55.18 | ROUGE1 | 74.6 |
| Thai LLM NLG - iapp_squad_seacrowd_qa (ROUGE2) | 43.73 | ROUGE2 | 74.6 |
| Thai LLM NLG - iapp_squad_seacrowd_qa (ROUGEL) | 54.78 | ROUGEL | 74.6 |
| Thai LLM - Social Science | 7.3 | Rating (0-10) | 65.5 |
| Thai LLM - STEM | 6.1 | Rating (0-10) | 58.5 |
| Thai LLM - Writing | 6.35 | Rating (0-10) | 57.7 |
| Thai LLM - Knowledge III | 3.9 | Rating (0-10) | 55.6 |
| Thai LLM NLG - xl_sum_tha_seacrowd_t2t (ROUGE2) | 9.29 | ROUGE2 | 53.7 |
| Thai LLM - Coding | 5.77 | Rating (0-10) | 51.4 |
| Thai LLM NLG - flores200_eng_Latn_tha_Thai_seacrowd_t2t (chrF++) | 48.66 | chrF++ | 50.7 |
| Thai LLM NLG - flores200_tha_Thai_eng_Latn_seacrowd_t2t (chrF++) | 57.09 | chrF++ | 50 |
| Thai LLM NLG - flores200_eng_Latn_tha_Thai_seacrowd_t2t (BLEU) | 21.75 | BLEU | 49.3 |
Interactive version: theaggregate.ai/model?slug=llama-3-typhoon-v1-5x-8b-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.