Safety Evaluation on Safety
92.1ScoreOlmo 3.1 32B Instruct
Evaluation results
| Method | Links | |
|---|---|---|
| Olmo 3.1 32B InstructStage=SFT2025.12 | 92.1 | |
| Olmo 3.1 32B InstructStage=Final Instruct 3.12025.12 | 89.5 | |
| Olmo 3.1 32B InstructStage=DPO2025.12 | 88.9 | |
| K2-V2 70B InstructModel Family=K2, Parameter Count=70B, Thinking Capability=false2025.12 | 88.5 | |
| Qwen 3 VL 32B InstructParameters=32B2025.12 | 85.8 | |
| OLMo 2 32BParameters=32B2025.12 | 84.2 | |
| Olmo 3.1 Think 32BTraining Stage=Final Think 3.1, Model Family=Olmo 3.1, Parameter Count=32B, Thinking Capability=true2025.12 | 83.6 | |
| Qwen 3 VL 8B Think2025.12 | 82.9 | |
| Qwen 3 VL 32B ThinkModel Family=Qwen 3, Parameter Count=32B, Thinking Capability=true2025.12 | 82.7 | |
| Qwen 2.5 32BParameters=32B2025.12 | 82.2 | |
| Qwen 3 32BThinking=No, Parameters=32B2025.12 | 81.6 | |
| Apertus 70BParameters=70B2025.12 | 77.1 | |
| Gemma 2 27BParameters=27B2025.12 | 74.4 | |
| Nemotron Nano 9B v22025.12 | 72.1 | |
| Olmo 3 7B ThinkStage=Final Think2025.12 | 70.7 | |
| Qwen 3 32BModel Family=Qwen 3, Parameter Count=32B, Thinking Capability=false2025.12 | 69 | |
| Olmo 3 Think (Final 3.0)Training Stage=Final Think 3.0, Model Family=Olmo 3, Parameter Count=32B, Thinking Capability=true2025.12 | 68.8 | |
| Gemma 3 27BParameters=27B2025.12 | 68.8 | |
| Qwen 3 8B2025.12 | 68.3 | |
| Olmo 3 7B ThinkStage=DPO2025.12 | 67.7 | |
| Olmo 3 7B ThinkStage=SFT2025.12 | 65.8 | |
| Olmo 3 Think (DPO)Training Stage=DPO, Model Family=Olmo 3, Parameter Count=32B, Thinking Capability=true2025.12 | 65.3 | |
| Olmo 3 Think (SFT)Training Stage=SFT, Model Family=Olmo 3, Parameter Count=32B, Thinking Capability=true2025.12 | 64.8 | |
| DS-R1 32BModel Family=DeepSeek-R1, Parameter Count=32B, Thinking Capability=true2025.12 | 63.6 | |
| DS-R1 Qwen 7B2025.12 | 54 | |
| OpenThinker3 7B2025.12 | 31.6 | |
| OR Nemotron 7B2025.12 | 30.3 |