GoTo-AI Leaderboard - IndoMMLU - Humanities: leaderboard
Metric: Score (0-100). Source: huggingface.co. 19 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek R1 Distill Llama 70B | 70.84 |
| 2 | Llama 3.3 70B Instruct | 70.13 |
| 3 | Llama 3.1 70B Instruct | 70.01 |
| 4 | Qwen 2.5 72B Instruct | 66.03 |
| 5 | Gemma 3 27B (IT) | 63.22 |
| 6 | DeepSeek R1 Distill Qwen 32B | 61.79 |
| 7 | gemma2-9B-cpt-sahabatai-v1-instruct | 58.04 |
| 8 | Gemma 2 9B (IT) | 55.98 |
| 9 | Qwen 2.5 7B Instruct | 48.73 |
| 10 | Llama 3.1 8B Instruct | 48.03 |
| 11 | Llama 3 8B Cpt Sahabatai V1 Instruct | 41.07 |
| 12 | Llama 3 8B Instruct | 40.5 |
| 13 | Qwen 2 7B Instruct | 27.82 |
Interactive version: theaggregate.ai/benchmark?slug=goto-ai-leaderboard-indommlu-humanities · How It Works · Data refreshed daily, snapshot 2026-09-19.