openthaigpt-1.0.0-7B-chat: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1239 ± 27, rank #9350 of 10916 rated models, from 33 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Thai LLM NLG - iapp_squad_seacrowd_qa (ROUGE1) | 50.55 | ROUGE1 | 68.7 |
| Thai LLM NLG - iapp_squad_seacrowd_qa (ROUGEL) | 50.02 | ROUGEL | 68.7 |
| Thai LLM NLG - iapp_squad_seacrowd_qa (ROUGE2) | 36.76 | ROUGE2 | 64.2 |
| Thai LLM NLU - xnli.tha_seacrowd_pairs | 34.25 | Accuracy (%) | 55.1 |
| Thai LLM NLG - flores200_eng_Latn_tha_Thai_seacrowd_t2t (SacreBLEU) | 29.73 | SacreBLEU | 38.8 |
| Thai LLM NLG - xl_sum_tha_seacrowd_t2t (ROUGEL) | 16.69 | ROUGEL | 37.3 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 47.09 | MC2 (%) (0-shot) | 36.4 |
| Thai LLM NLG - xl_sum_tha_seacrowd_t2t (ROUGE1) | 24.58 | ROUGE1 | 35.8 |
| Thai LLM NLG - flores200_eng_Latn_tha_Thai_seacrowd_t2t (chrF++) | 44.9 | chrF++ | 34.3 |
| Thai LLM NLG - flores200_eng_Latn_tha_Thai_seacrowd_t2t (BLEU) | 18.43 | BLEU | 33.6 |
| Open LLM Leaderboard v1 - GSM8K | 5.23 | Accuracy (%) (5-shot) | 23.8 |
| Open LLM Leaderboard v1 - HellaSwag | 71.31 | Normalized accuracy (%) (10-shot) | 21.4 |
Interactive version: theaggregate.ai/model?slug=openthaigpt-1-0-0-7b-chat · How It Works · Data refreshed daily, snapshot 2026-11-08.