Tsunami-0.5-7B-Instruct: benchmark results
Provider: Tsunami-th. Released 2024-10-11. Access: Open.
Aggregate Rating 1518 ± 35, rank #2088 of 10916 rated models, from 33 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MATH Level 5 | 50.45 | Score | 97.2 |
| Open LLM Leaderboard - IFEval | 74 | Score | 88.9 |
| Open LLM Leaderboard - MMLU-Pro | 44.13 | Score | 81.8 |
| Open LLM Leaderboard - BBH | 55.24 | Score | 74.4 |
| Thai LLM NLU - xnli.tha_seacrowd_pairs | 39.18 | Accuracy (%) | 73.9 |
| Thai LLM NLU - wisesight_thai_sentiment_seacrowd_text | 49.12 | Accuracy (%) | 72.5 |
| Thai LLM - Coding | 6.91 | Rating (0-10) | 71.1 |
| Thai LLM - Reasoning | 5.55 | Rating (0-10) | 66.9 |
| Open LLM Leaderboard - GPQA | 30.87 | Score | 66.2 |
| Open LLM Leaderboard - MuSR | 42.57 | Score | 66.2 |
| Thai LLM NLU - xcopa_tha_seacrowd_qa | 88.2 | Accuracy (%) | 65.2 |
| Thai LLM - STEM | 6.25 | Rating (0-10) | 63.4 |
Interactive version: theaggregate.ai/model?slug=tsunami-0-5-7b-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.