Sahabat-AI - Javanese (JV): leaderboard
Sahabat-AI Javanese-language evaluation — aggregate performance on reasoning, knowledge and language tasks in Javanese; average score.
Metric: Score (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 17 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | gemma2-9B-cpt-sahabatai-v1-instruct | 60.1 | #609 |
| 2 | Llama 3 8B Cpt Sahabatai V1 Instruct | 49.64 | #906 |
| 3 | Gemma 2 9B (IT) | 43.36 | #789 |
| 4 | Gemma 2 9B | 42.83 | #957 |
| 5 | Llama 3.1 8B | 41.53 | #1148 |
| 6 | Llama 3 8B | 40.04 | #1243 |
| 7 | Llama 3 8B Cpt Sea Lionv2 Base | 38.94 | #1182 |
| 8 | Llama 3.1 8B Instruct | 35.26 | #1035 |
| 9 | Qwen 2.5 7B | 34.11 | #921 |
| 10 | Llama 3 8B Cpt Sea Lionv2.1 Instruct | 33.2 | #1018 |
| 11 | Qwen 2.5 7B Instruct | 30.47 | #863 |
| 12 | Qwen 2 7B | 29.87 | #1095 |
| 13 | Llama 3 8B Instruct | 28.91 | #1131 |
| 14 | Qwen 2 7B Instruct | 23.29 | #991 |
No result here: #4 Claude Opus 5.5, #6 GPT-6 Astra, #7 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=sahabat-ai-javanese-jv · How It Works · Data refreshed daily, snapshot 2026-10-21.