Perception on OneReason-Bench
36.91Item UnderstandingOneReason SFT thinking
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| OneReason SFT thinkingCategory=Itemic Token-Based, Thinking Mode=thinking, Stage=SFT2026.06 | 36.91 | 1.06 | 64.6 | |
| OneReason SFT non-thinkingCategory=Itemic Token-Based, Thinking Mode=non-thinking, Stage=SFT2026.06 | 36.84 | 3.95 | 66.55 | |
| OneReason RFT non-thinkingCategory=Itemic Token-Based, Thinking Mode=non-thinking, Stage=RFT2026.06 | 36.82 | 5.24 | 67.25 | |
| OneReason RFT thinkingCategory=Itemic Token-Based, Thinking Mode=thinking, Stage=RFT2026.06 | 36.78 | 1.35 | 65.65 | |
| LC-Rec-PT-SFT-8BCategory=Itemic Token-Based2026.06 | 35.41 | 5.21 | 63.9 | |
| LC-Rec-SFT-Only-14BCategory=Itemic Token-Based2026.06 | 26.48 | 0 | 56.45 | |
| LC-Rec-SFT-Only-8BCategory=Itemic Token-Based2026.06 | 22.98 | 0 | 0.4 |