List your company

Evolution on OneReason-Bench

58.92Selection ScoreGPT-5.4
-2.356813.551629.4645.3684Jun 4, 2026

Evaluation results

MethodLinks
GPT-5.4Category=Text-Based2026.0658.9241.4117.61
Deepseek-V3.2Category=Text-Based2026.0657.1827.1311.32
Claude-Opus-4.6Category=Text-Based2026.0656.8417.1613.46
Gemini-3-PreviewCategory=Text-Based2026.0656.8333.6814.76
Qwen3-32BCategory=Text-Based2026.0651.9628.057.73
OneReason RFT thinkingCategory=Itemic Token-Based, Thinking Mode=thinking, Stage=RFT2026.0642.4239.5721.23
Qwen3-8BCategory=Text-Based2026.0640.725.498.6
OneReason RFT non-thinkingCategory=Itemic Token-Based, Thinking Mode=non-thinking, Stage=RFT2026.0638.9239.3320.31
OneReason SFT non-thinkingCategory=Itemic Token-Based, Thinking Mode=non-thinking, Stage=SFT2026.0635.0733.8715.42
OneReason SFT thinkingCategory=Itemic Token-Based, Thinking Mode=thinking, Stage=SFT2026.0632.1831.614.31
LC-Rec-PT-SFT-8BCategory=Itemic Token-Based2026.063.328.64.46
LC-Rec-SFT-Only-8BCategory=Itemic Token-Based2026.06000
LC-Rec-SFT-Only-14BCategory=Itemic Token-Based2026.06000