gemma2-9B-cpt-sea-lionv3-base: benchmark results
Provider: Other.
Aggregate Rating 1498 ± 26, rank #2396 of 10916 rated models, from 12 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Sahabat-AI - Indonesian Average | 49.23 | Average Score (%) | 81.2 |
| Sahabat-AI - Sundanese (SU) | 44.95 | Score (%) | 81.2 |
| Sahabat-AI - Indonesian (ID) | 55.09 | Score (%) | 75 |
| Sahabat-AI - Javanese (JV) | 47.65 | Score (%) | 75 |
| SEA LLM Leaderboard - SeaExam - Vietnamese (Public) | 68 | Public Accuracy (%) | 67.2 |
| SEA LLM Leaderboard - SeaExam - Vietnamese (Private) | 71 | Private Accuracy (%) | 62.2 |
| SEA LLM Leaderboard - SeaExam (Public) | 60.4 | Public Average Score (%) | 55.6 |
| SEA LLM Leaderboard - SeaExam - Thai (Public) | 57.4 | Public Accuracy (%) | 54.4 |
| SEA LLM Leaderboard - SeaExam - Indonesian (Public) | 55.9 | Public Accuracy (%) | 53.3 |
| SEA LLM Leaderboard - SeaExam | 59.2 | Private Average Score (%) | 51.1 |
| SEA LLM Leaderboard - SeaExam - Indonesian (Private) | 58.8 | Private Accuracy (%) | 46.7 |
| SEA LLM Leaderboard - SeaExam - Thai (Private) | 47.8 | Private Accuracy (%) | 46.7 |
Interactive version: theaggregate.ai/model?slug=gemma2-9b-cpt-sea-lionv3-base · How It Works · Data refreshed daily, snapshot 2026-11-08.