Logical Reasoning on LogicVista (test)
60.3AccuracyRTWI
Evaluation Results
| Method | Links | |
|---|---|---|
| RTWIModel Variant=Qwen3-VL Instruct, Setting=Offline2026.02 | 60.3 | |
| RTWIModel Variant=Qwen3-VL Thinking, Setting=Offline2026.02 | 59.1 | |
| DeepconfModel Variant=Qwen3-VL Instruct, Setting=Offline2026.02 | 55.4 | |
| Self-Cer.Model Variant=Qwen3-VL Instruct, Setting=Offline2026.02 | 55.4 | |
| CISCModel Variant=Qwen3-VL Instruct, Setting=Offline2026.02 | 55.3 | |
| SCModel Variant=Qwen3-VL Instruct, Setting=Offline2026.02 | 54.8 | |
| DeepconfModel Variant=Qwen3-VL Thinking, Setting=Offline2026.02 | 50.8 | |
| CISCModel Variant=Qwen3-VL Thinking, Setting=Offline2026.02 | 50.2 | |
| Self-Cer.Model Variant=Qwen3-VL Thinking, Setting=Offline2026.02 | 49.1 | |
| BaseModel Variant=Qwen3-VL Instruct, Setting=Offline2026.02 | 47.9 | |
| SCModel Variant=Qwen3-VL Thinking, Setting=Offline2026.02 | 46.4 | |
| BaseModel Variant=Qwen3-VL Thinking, Setting=Offline2026.02 | 44.3 |