General Tasks on MMLU-redux
86.8AccuracyQwen2.5-72B
Evaluation results
| Method | Links | |
|---|---|---|
| Qwen2.5-72BModel Type=Instruct, Parameters=72B2025.02 | 86.8 | |
| Llama-3.1-405BModel Type=Instruct, Parameters=405B2025.02 | 86.2 | |
| Qwen2.5-VL-72BModel Type=Instruct, Parameters=72B2025.02 | 85.9 | |
| Llama-3.1-70BModel Type=Instruct, Parameters=70B2025.02 | 83 | |
| Qwen2-72BModel Type=Instruct, Parameters=72B2025.02 | 81.6 | |
| Fine-tunedBase LLM=Qwen-2.5-7B-Instruct, Parameters=x42026.05 | 76.6 | |
| DiDi-Merg.-LBase LLM=Qwen-2.5-7B-Instruct, Parameters=x2.02026.05 | 76.2 | |
| FREE-MergingBase LLM=Qwen-2.5-7B-Instruct, Parameters=x2.082026.05 | 75.2 | |
| Zero-shotBase LLM=Qwen-2.5-7B-Instruct, Parameters=x12026.05 | 75.1 | |
| Twin-MergingBase LLM=Qwen-2.5-7B-Instruct, Parameters=x2.252026.05 | 74.8 | |
| Fine-tunedBase LLM=Llama-3.1-8B-Instruct, Parameters=x42026.05 | 73 | |
| DiDi-Merg.-LBase LLM=Llama-3.1-8B-Instruct, Parameters=x2.02026.05 | 72.8 | |
| Twin-MergingBase LLM=Llama-3.1-8B-Instruct, Parameters=x2.252026.05 | 72.6 | |
| FREE-MergingBase LLM=Llama-3.1-8B-Instruct, Parameters=x2.082026.05 | 72.4 | |
| Zero-shotBase LLM=Llama-3.1-8B-Instruct, Parameters=x12026.05 | 70.5 |