General Knowledge on MMLU-redux (Accuracy)
90.6AccuracyMiMo-V2-Flash Base
Evaluation results
| Method | Links | |
|---|---|---|
| MiMo-V2-Flash Base# Shots=5-shot, # Activated Params=15B, # Total Params=309B2026.01 | 90.6 | |
| DeepSeek-V3.2 Exp Base# Shots=5-shot, # Activated Params=37B, # Total Params=671B2026.01 | 90.4 | |
| Kimi-K2 Base# Shots=5-shot, # Activated Params=32B, # Total Params=1043B2026.01 | 90.2 | |
| DeepSeek-V3.1 Base# Shots=5-shot, # Activated Params=37B, # Total Params=671B2026.01 | 90 | |
| RMoAModel=GPT-4o2025.05 | 86.67 | |
| MoAModel=GPT-4o2025.05 | 85.8 | |
| SMoAModel=GPT-4o2025.05 | 84.94 | |
| GPT-4oModel=GPT-4o2025.05 | 83.73 | |
| Qwen2.5-7B-InstructModel=Qwen2.5-7B-Instruct2026.03 | 75.6 | |
| Ministral-3-8B-Instruct-2512Model=Ministral-3-8B-Instruct-25122026.03 | 74.2 | |
| SMoAModel=Qwen2.5-7B-Instruct2025.05 | 72 | |
| RMoAModel=Qwen2.5-7B-Instruct2025.05 | 71.8 | |
| Qwen2.5-7B-InstructModel=Qwen2.5-7B-Instruct2025.05 | 69.9 | |
| Llama-3.1-8B-InstructModel=Llama-3.1-8B-Instruct2026.03 | 69.6 | |
| RMoAModel=Gemma2-9B-Instruct2025.05 | 66.1 | |
| Llama-EstLLM-8B-Instruct-CVModel=Llama-EstLLM-8B-Instruct-CV2026.03 | 66.1 | |
| SMoAModel=Gemma2-9B-Instruct2025.05 | 65.8 | |
| MoAModel=Gemma2-9B-Instruct2025.05 | 65.73 | |
| Gemma2-9B-InstructModel=Gemma2-9B-Instruct2025.05 | 63.9 | |
| Llama-EstLLM-8B-InstructModel=Llama-EstLLM-8B-Instruct2026.03 | 63.9 | |
| MoAModel=Qwen2.5-7B-Instruct2025.05 | 62.7 | |
| RMoAModel=Llama3.1-8B-Instruct2025.05 | 61.63 | |
| Apertus-8B-Instruct-2509Model=Apertus-8B-Instruct-25092026.03 | 61 | |
| SMoAModel=Llama3.1-8B-Instruct2025.05 | 60.86 | |
| Apertus-EstLLM-InstructModel=Apertus-EstLLM-Instruct2026.03 | 59.4 | |
| Llama3.1-8B-InstructModel=Llama3.1-8B-Instruct2025.05 | 58.6 | |
| EuroLLM-9B-InstructModel=EuroLLM-9B-Instruct2026.03 | 57.4 | |
| MoAModel=Llama3.1-8B-Instruct2025.05 | 55.1 | |
| salamandra-7b-instructModel=salamandra-7b-instruct2026.03 | 51.8 | |
| LlammasModel=Llammas2026.03 | 34.2 |