Aggregated Logical Reasoning on Overall Unsolvable
0.945AccuracyGPT-5.1-Low
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-5.1-LowModel=GPT-5.1-Low2025.12 | 0.945 | |
| Gemini-3.0-ProModel=Gemini-3.0-Pro2025.12 | 0.855 | |
| Deepseek-V3.2-RModel=Deepseek-V3.2-R2025.12 | 0.85 | |
| Qwen3-4B-Instruct + UnsolRL-FinalBase Model=Qwen3-4B-Instruct, Method=UnsolRL-Final2025.12 | 0.524 | |
| Qwen3-4B-InstructModel=Qwen3-4B-Instruct2025.12 | 0.345 | |
| Qwen3-1.7B-Instruct + UnsolRL-FinalBase Model=Qwen3-1.7B-Instruct, Method=UnsolRL-Final2025.12 | 0.242 | |
| Qwen3-1.7B-InstructModel=Qwen3-1.7B-Instruct2025.12 | 0.18 |