llama-3-typhoon-v1.5x-70B-instruct: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1564 ± 41, rank #1494 of 10916 rated models, from 27 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Thai LLM - Extraction | 7.05 | Rating (0-10) | 90.1 |
| Thai LLM - STEM | 7.15 | Rating (0-10) | 88.7 |
| Thai LLM - Writing | 7.45 | Rating (0-10) | 87.3 |
| Thai LLM MC - thaiexam_qa | 58.76 | Accuracy (%) | 84.1 |
| Thai LLM - Social Science | 8.3 | Rating (0-10) | 83.1 |
| Thai LLM NLU - belebele_tha_thai_seacrowd_qa | 85.56 | Accuracy (%) | 81.2 |
| Thai LLM - Knowledge III | 4.8 | Rating (0-10) | 80.3 |
| Thai LLM NLG - xl_sum_tha_seacrowd_t2t (ROUGE2) | 10.5 | ROUGE2 | 79.9 |
| Thai LLM MC - m3exam_tha_seacrowd_qa | 59.92 | Accuracy (%) | 78.3 |
| Thai LLM NLU - xcopa_tha_seacrowd_qa | 90.6 | Accuracy (%) | 78.3 |
| Thai LLM - Math | 6.35 | Rating (0-10) | 75.4 |
| Thai LLM NLG - flores200_tha_Thai_eng_Latn_seacrowd_t2t (chrF++) | 59 | chrF++ | 75.4 |
Interactive version: theaggregate.ai/model?slug=llama-3-typhoon-v1-5x-70b-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.