List your company

Derivation on OneReason-Bench

28.6I2I ScoreOneReason RFT thinking
2.42329.219116.01522.8109Jun 4, 2026

Evaluation results

MethodLinks
OneReason RFT thinkingCategory=Itemic Token-Based, Thinking Mode=thinking, Stage=RFT2026.0628.6
OneReason SFT non-thinkingCategory=Itemic Token-Based, Thinking Mode=non-thinking, Stage=SFT2026.0628.36
LC-Rec-PT-SFT-8BCategory=Itemic Token-Based2026.0625.54
OneReason RFT non-thinkingCategory=Itemic Token-Based, Thinking Mode=non-thinking, Stage=RFT2026.0623.99
OneReason SFT thinkingCategory=Itemic Token-Based, Thinking Mode=thinking, Stage=SFT2026.0623.88
LC-Rec-SFT-Only-14BCategory=Itemic Token-Based2026.0616.21
LC-Rec-SFT-Only-8BCategory=Itemic Token-Based2026.063.43