List your company

Mathematical Reasoning on AMC 23 (Accuracy, Pass@8)

90.9AccuracyQwen3-8B (Thinking)
10.331.22552.1573.075May 16, 2026

Evaluation results

MethodLinks
Qwen3-8B (Thinking)Model=Qwen3-8B, Variant=Thinking2026.0590.9100
Qwen3-1.7B (Thinking)Model=Qwen3-1.7B, Variant=Thinking2026.058095
Qwen3-1.7B + Guided (ρ¯ ≈ 0.16)Model=Qwen3-1.7B, Intervention Rate (rho)=≈ 0.162026.0571.997.5
Qwen3-0.6B + Guided (ρ¯ ≈ 0.13)Model=Qwen3-0.6B, Intervention Rate (rho)=≈ 0.132026.0558.490
Qwen3-1.7B + Guided (ρ¯ ≈ 0.06)Model=Qwen3-1.7B, Intervention Rate (rho)=≈ 0.062026.0550.695
Qwen3-0.6B (Thinking)Model=Qwen3-0.6B, Variant=Thinking2026.0546.980
Qwen3-0.6B + Guided (ρ¯ ≈ 0.04)Model=Qwen3-0.6B, Intervention Rate (rho)=≈ 0.042026.0535.977.5
Qwen3-1.7B-BaseModel=Qwen3-1.7B, Variant=Base2026.0528.165
Qwen3-0.6B-BaseModel=Qwen3-0.6B, Variant=Base2026.0513.442.5