Reasoning on LiveCodeBench
54.25LiveCodeBench ScoreDeepSeek-R1-Distill-Qwen-32B (Reasoning)
Evaluation results
| Method | Links | |
|---|---|---|
| DeepSeek-R1-Distill-Qwen-32B (Reasoning)Model Family=Qwen2.5-32B2026.01 | 54.25 | |
| DeepSeek-R1-Distill-Qwen-14B (Reasoning)Model Family=Qwen2.5-14B2026.01 | 48.15 | |
| ReasonAnyModel Family=Qwen2.5-32B2026.01 | 46.16 | |
| ReasonAnyModel Family=Qwen2.5-14B2026.01 | 44.35 | |
| Task ArithmeticModel Family=Qwen2.5-14B2026.01 | 39.27 | |
| LEDModel Family=Qwen2.5-32B2026.01 | 38.6 | |
| TIESModel Family=Qwen2.5-14B2026.01 | 30.81 | |
| LEDModel Family=Qwen2.5-14B2026.01 | 30.35 | |
| ReasoningBase Model=Llama-3.1-8B2026.01 | 29.91 | |
| Qwen2.5-14B-Instruct (Safety)Model Family=Qwen2.5-14B2026.01 | 27.31 | |
| FuseLLMModel Family=Qwen2.5-32B2026.01 | 25.89 | |
| DAREModel Family=Qwen2.5-32B2026.01 | 23.78 | |
| Qwen2.5-32B-Instruct (Safety)Model Family=Qwen2.5-32B2026.01 | 23.39 | |
| ReasonAnyMerging Protocol=ReasonAny2026.01 | 23.38 | |
| TIESModel Family=Qwen2.5-32B2026.01 | 21.86 | |
| LEDMerging Protocol=LED2026.01 | 20.38 | |
| TIESMerging Protocol=TIES2026.01 | 19.94 | |
| Task ArithmeticModel Family=Qwen2.5-32B2026.01 | 19.75 | |
| LinearModel Family=Qwen2.5-32B2026.01 | 17.55 | |
| FuseLLMModel Family=Qwen2.5-14B2026.01 | 14.48 | |
| LinearMerging Protocol=Linear2026.01 | 14 | |
| LinearModel Family=Qwen2.5-14B2026.01 | 13.33 | |
| SafetyBase Model=Llama-3.1-8B2026.01 | 12.43 | |
| DAREModel Family=Qwen2.5-14B2026.01 | 8.34 | |
| DAREMerging Protocol=DARE2026.01 | 5.27 | |
| FuseLLMMerging Protocol=FuseLLM2026.01 | 3.58 | |
| Task ArithmeticMerging Protocol=Task Arithmetic2026.01 | 0.86 |