Tsunami-1.0-14B-Instruct: benchmark results
Provider: Tsunami-th. Released 2024-10-25. Access: Open.
Aggregate Rating 1568 ± 39, rank #1435 of 10916 rated models, from 33 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - IFEval | 78.29 | Score | 94.7 |
| Open LLM Leaderboard - MATH Level 5 | 45.85 | Score | 94 |
| Thai LLM MC - thaiexam_qa | 61.06 | Accuracy (%) | 92.8 |
| Open LLM Leaderboard - MMLU-Pro | 52.49 | Score | 91.1 |
| Thai LLM MC - m3exam_tha_seacrowd_qa | 63.05 | Accuracy (%) | 90.6 |
| Open LLM Leaderboard - GPQA | 35.65 | Score | 89.9 |
| Open LLM Leaderboard - BBH | 64.39 | Score | 89.4 |
| Thai LLM NLU - xnli.tha_seacrowd_pairs | 42.57 | Accuracy (%) | 88.4 |
| Thai LLM NLG - flores200_tha_Thai_eng_Latn_seacrowd_t2t (chrF++) | 59.96 | chrF++ | 88.1 |
| Thai LLM NLU - wisesight_thai_sentiment_seacrowd_text | 51.18 | Accuracy (%) | 85.5 |
| Open LLM Leaderboard - MuSR | 44.59 | Score | 81.3 |
| Thai LLM - Math | 6.45 | Rating (0-10) | 79.6 |
Interactive version: theaggregate.ai/model?slug=tsunami-1-0-14b-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.