Reasoning on Math (General Score)
94.2Math ScoreDeepSeek-R1-Distill-Qwen-32B (Reasoning)
Evaluation results
| Method | Links | |
|---|---|---|
| DeepSeek-R1-Distill-Qwen-32B (Reasoning)Model Family=Qwen2.5-32B2026.01 | 94.2 | |
| ReasonAnyModel Family=Qwen2.5-32B2026.01 | 92.4 | |
| DeepSeek-R1-Distill-Qwen-14B (Reasoning)Model Family=Qwen2.5-14B2026.01 | 92.4 | |
| DAREModel Family=Qwen2.5-32B2026.01 | 83.4 | |
| ReasonAnyModel Family=Qwen2.5-14B2026.01 | 83.2 | |
| Task ArithmeticModel Family=Qwen2.5-32B2026.01 | 82.8 | |
| Qwen2.5-32B-Instruct (Safety)Model Family=Qwen2.5-32B2026.01 | 82.2 | |
| LinearModel Family=Qwen2.5-32B2026.01 | 81.2 | |
| Task ArithmeticModel Family=Qwen2.5-14B2026.01 | 81 | |
| LinearModel Family=Qwen2.5-14B2026.01 | 80.8 | |
| FuseLLMModel Family=Qwen2.5-32B2026.01 | 79.6 | |
| LEDModel Family=Qwen2.5-32B2026.01 | 78.4 | |
| DAREModel Family=Qwen2.5-14B2026.01 | 77.8 | |
| Qwen2.5-14B-Instruct (Safety)Model Family=Qwen2.5-14B2026.01 | 76.6 | |
| LEDModel Family=Qwen2.5-14B2026.01 | 76.6 | |
| TIESModel Family=Qwen2.5-32B2026.01 | 76.2 | |
| FuseLLMModel Family=Qwen2.5-14B2026.01 | 75.4 | |
| TIESModel Family=Qwen2.5-14B2026.01 | 70 | |
| ReasoningBase Model=Llama-3.1-8B2026.01 | 64.4 | |
| ReasonAnyMerging Protocol=ReasonAny2026.01 | 52.3 | |
| LinearMerging Protocol=Linear2026.01 | 37.4 | |
| DAREMerging Protocol=DARE2026.01 | 30.6 | |
| Task ArithmeticMerging Protocol=Task Arithmetic2026.01 | 22.8 | |
| TIESMerging Protocol=TIES2026.01 | 15 | |
| LEDMerging Protocol=LED2026.01 | 6.4 | |
| SafetyBase Model=Llama-3.1-8B2026.01 | 3 | |
| FuseLLMMerging Protocol=FuseLLM2026.01 | 2.2 |