GoTo-AI Leaderboard - IndoMMLU: leaderboard
GoTo-AI Leaderboard (GoToCompany, successor of the Sahabat-AI leaderboard), evaluating mostly open 7-72B models. IndoMMLU (Koto et al., 2023) Indonesian school-exam multiple-choice questions, overall score on 0-100 (higher is better); published for instruct and reasoning models only.
Metric: Score (0-100). Source: huggingface.co. Saturation forecast: Estimated already saturated. 19 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | DeepSeek R1 Distill Llama 70B | 63.62 | #614 |
| 2 | Llama-SEA-LION-v3-70B-IT | 60.18 | #407 |
| 3 | Llama 3.1 70B Instruct | 59.21 | #567 |
| 4 | Llama 3.3 70B Instruct | 58.95 | #541 |
| 5 | Gemma 3 27B (IT) | 57 | #528 |
| 6 | DeepSeek R1 Distill Qwen 32B | 56.97 | #662 |
| 7 | Qwen 2.5 72B Instruct | 56.41 | #469 |
| 8 | gemma2-9B-cpt-sahabatai-v1-instruct | 52.11 | #618 |
| 9 | Gemma 2 9B (IT) | 49 | #795 |
| 10 | Qwen 2.5 7B Instruct | 42.71 | #863 |
| 11 | Llama 3.1 8B Instruct | 40.89 | #1017 |
| 12 | Llama 3 8B Instruct | 32.81 | #1116 |
| 13 | Llama 3 8B Cpt Sahabatai V1 Instruct | 31.99 | #905 |
| 14 | Qwen 2 7B Instruct | 19.44 | #982 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=goto-ai-leaderboard-indommlu · How It Works · Data refreshed daily, snapshot 2026-11-05.