List your company

Mathematical Reasoning on AIME (Error Attribution Scores)

46Random ScoreQWEN3 8B
16.98424.51732.0539.583Apr 6, 2026

Evaluation results

MethodLinks
QWEN3 8Bn=82026.044646.946.145.549.550.348.943.7
QWEN3 8Bn=322026.0445.847.746.93951.254.950.438.3
QWEN3 8Bn=42026.0445.746.645.945.948.848.848.244.4
QWEN3 8Bn=162026.0445.347.146.141.750.451.649.244.1
QWEN3 4Bn=162026.0440.442.441.137.842.348.345.733.3
QWEN3 4Bn=42026.0440.241.140.441.140.743.14140
QWEN3 4Bn=322026.0439.74842.236.448.950.552.331.9
QWEN3 4Bn=82026.043941.840.639.142.545.540.336.7
DISTILL-QWEN 7Bn=42026.0424.727.225.421.232.431.926.724.5
DISTILL-QWEN 7Bn=322026.0424.429.729.718.635.134.231.120.2
DISTILL-QWEN 7Bn=82026.0424.327.725.720.432.732.529.224
DISTILL-QWEN 7Bn=162026.0424.128.126.620.133.133.129.522.7
DISTILL-QWEN 1.5Bn=82026.0418.418.119.612.422.122.220.818.3
DISTILL-QWEN 1.5Bn=322026.0418.320.42013.324.622.822.117.5
DISTILL-QWEN 1.5Bn=42026.0418.118.419.213.62121.820.218.1
DISTILL-QWEN 1.5Bn=162026.0418.118.819.912.222.322.421.117.6