Aggregated Logical Reasoning on Overall Solvable
67.3AccuracyDeepseek-V3.2-R
Evaluation Results
| Method | Links | |
|---|---|---|
| Deepseek-V3.2-RModel=Deepseek-V3.2-R2025.12 | 67.3 | |
| Gemini-3.0-ProModel=Gemini-3.0-Pro2025.12 | 54.3 | |
| GPT-5.1-LowModel=GPT-5.1-Low2025.12 | 38.5 | |
| Qwen3-4B-Instruct + UnsolRL-FinalBase Model=Qwen3-4B-Instruct, Method=UnsolRL-Final2025.12 | 17.4 | |
| Qwen3-4B-InstructModel=Qwen3-4B-Instruct2025.12 | 11.8 | |
| Qwen3-1.7B-InstructModel=Qwen3-1.7B-Instruct2025.12 | 4.9 | |
| Qwen3-1.7B-Instruct + UnsolRL-FinalBase Model=Qwen3-1.7B-Instruct, Method=UnsolRL-Final2025.12 | 3.3 |