Sahabat-AI - Indonesian (ID): leaderboard
Sahabat-AI Indonesian-language evaluation — aggregate performance on reasoning, knowledge and language tasks in Indonesian; 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 | 63.96 | #608 |
| 2 | Gemma 2 9B (IT) | 63.09 | #788 |
| 3 | Qwen 2.5 7B Instruct | 59.2 | #862 |
| 4 | Llama 3 8B Cpt Sahabatai V1 Instruct | 56.56 | #910 |
| 5 | Llama 3 8B Cpt Sea Lionv2.1 Instruct | 54.35 | #1024 |
| 6 | Qwen 2.5 7B | 51.66 | #922 |
| 7 | Llama 3.1 8B Instruct | 50.52 | #1035 |
| 8 | Gemma 2 9B | 48.02 | #958 |
| 9 | Qwen 2 7B Instruct | 46.25 | #991 |
| 10 | Qwen 2 7B | 44.81 | #1095 |
| 11 | Llama 3 8B Cpt Sea Lionv2 Base | 42.45 | #1182 |
| 12 | Llama 3.1 8B | 41.93 | #1151 |
| 13 | Llama 3 8B Instruct | 41.36 | #1129 |
| 14 | Llama 3 8B | 41.14 | #1242 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=sahabat-ai-indonesian-id · How It Works · Data refreshed daily, snapshot 2026-10-20.