Code Generation on LiveCodeBench v3
90.2ScoreQwen 3 32B
Evaluation results
| Method | Links | |
|---|---|---|
| Qwen 3 32BModel Family=Qwen 3, Parameter Count=32B, Thinking Capability=false2025.12 | 90.2 | |
| Qwen 3 8B2025.12 | 86.2 | |
| Qwen 3 VL 8B Think2025.12 | 85.5 | |
| Qwen 3 VL 32B ThinkModel Family=Qwen 3, Parameter Count=32B, Thinking Capability=true2025.12 | 84.8 | |
| Olmo 3 Think (Final 3.0)Training Stage=Final Think 3.0, Model Family=Olmo 3, Parameter Count=32B, Thinking Capability=true2025.12 | 83.5 | |
| Nemotron Nano 9B v22025.12 | 83.4 | |
| Olmo 3.1 Think 32BTraining Stage=Final Think 3.1, Model Family=Olmo 3.1, Parameter Count=32B, Thinking Capability=true2025.12 | 83.3 | |
| OR Nemotron 7B2025.12 | 82.3 | |
| Olmo 3 Think (DPO)Training Stage=DPO, Model Family=Olmo 3, Parameter Count=32B, Thinking Capability=true2025.12 | 81.9 | |
| DS-R1 32BModel Family=DeepSeek-R1, Parameter Count=32B, Thinking Capability=true2025.12 | 79.5 | |
| K2-V2 70B InstructModel Family=K2, Parameter Count=70B, Thinking Capability=false2025.12 | 78.4 | |
| Olmo 3 Think (SFT)Training Stage=SFT, Model Family=Olmo 3, Parameter Count=32B, Thinking Capability=true2025.12 | 75.8 | |
| Olmo 3 7B ThinkStage=Final Think2025.12 | 75.2 | |
| Olmo 3 7B ThinkStage=DPO2025.12 | 75.1 | |
| OpenThinker3 7B2025.12 | 68 | |
| Olmo 3 7B ThinkStage=SFT2025.12 | 67.8 | |
| DS-R1 Qwen 7B2025.12 | 58.8 | |
| Qwen 3 VL 8B Inststage=Instruct2025.12 | 55.9 | |
| Qwen 3 8Bstage=Instruct2025.12 | 53.2 | |
| Qwen 2.5 7Bstage=Instruct2025.12 | 34.5 | |
| Olmo 3 7B Instructstage=Final Instruct2025.12 | 29.5 | |
| Olmo 3 7B Instructstage=SFT2025.12 | 20 | |
| Olmo 3 7B Instructstage=DPO2025.12 | 18.8 | |
| Granite 3.3 8B Inststage=Instruct2025.12 | 11.5 | |
| Apertus 8B Inststage=Instruct2025.12 | 7.8 | |
| OLMo 2 7B Inststage=Instruct2025.12 | 7.2 |