Tsunami-0.5x-7B-Instruct: benchmark results
Provider: Tsunami-th. Released 2024-10-15. Access: Open.
Aggregate Rating 1513 ± 37, rank #2141 of 10916 rated models, from 33 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MATH Level 5 | 42.07 | Score | 91.6 |
| Open LLM Leaderboard - MuSR | 46.67 | Score | 90.1 |
| Thai LLM NLU - xnli.tha_seacrowd_pairs | 41.96 | Accuracy (%) | 87 |
| Open LLM Leaderboard - IFEval | 70.99 | Score | 84.2 |
| Open LLM Leaderboard - MMLU-Pro | 44.58 | Score | 82.7 |
| Open LLM Leaderboard - BBH | 55.93 | Score | 76.8 |
| Thai LLM NLG - xl_sum_tha_seacrowd_t2t (ROUGE2) | 10.26 | ROUGE2 | 76.1 |
| Thai LLM NLG - xl_sum_tha_seacrowd_t2t (ROUGE1) | 29.15 | ROUGE1 | 71.6 |
| Thai LLM NLG - xl_sum_tha_seacrowd_t2t (ROUGEL) | 19.55 | ROUGEL | 71.6 |
| Open LLM Leaderboard - GPQA | 31.46 | Score | 71.3 |
| Thai LLM NLU - belebele_tha_thai_seacrowd_qa | 81.11 | Accuracy (%) | 68.1 |
| Thai LLM MC - m3exam_tha_seacrowd_qa | 54.11 | Accuracy (%) | 65.2 |
Interactive version: theaggregate.ai/model?slug=tsunami-0-5x-7b-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.