Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Chain-of-Thought Reasoning on Reasoning Dataset

86.9Accuracy (Acc)

Qwen3-30B-A3B-Thinking-2507

54.76463.10771.4579.793Mar 7, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
86.95,077.393.10.019145.71.6565.675.3411.413.21268.868.4
2026.03
86.85,823117.40.02178.41.65.535.231012.912.369.360.8
2026.03
85.51,462.3260.00341.71.6613.723.5410.27.49.650.217.1
2026.03
85.36,954.8181.20.1052651.6171.591.641512.346.886.595.5
2026.03
83.21,794.345.90.06863.91.4843.12.959.87.510.35838.2
2026.03
82.84,313.4149.80.032331.7496.846.711.2712.47863.6
2026.03
82.41,080.121.50.03328.21.3312.652.518.84.49.133.616.4
2026.03
82.12,673.661.80.048101.71.6685.37511.25.98.866.764.6
2026.03
80.88,816.8303.10.059449.11.6776.21613.911.812.374.282
2026.03
80.32,75635.80.00459.91.7614.414.2112.37.29.854.924.1
2026.03
79.75,146.613.40.02715.71.233.12.83.37.78.937.73.7
2026.03
79.63,402.891.90.026152.11.9646.316.3114.78.210.172.569.4
2026.03
78.93,557130.03214.81.22932.956.98.939.37.3
2026.03
77.82,474.442.10.03169.11.7845.745.414.968.668.756.1
2026.03
77.5450.521.80.012241.1382.712.598.78.211.936.83.1
2026.03
75.82,185.634.40.05151.51.3672.442.328.19.58.849.836.6
2026.03
71.73,256.196.20.0351421.4095.795.5711811.275.442.7
2026.03
70.82,14163.50.03891.91.2754.344.28.15.911.169.928.2
2026.03
70.34,160.410.70.0411.21.1292.061.94515.3733.34.9
2026.03
59.85,090.6159.20.025225.71.5834.94.8111.710.812.275.362.6
2026.03
563,596.5108.70.038153.21.4424.774.5311.88.312.97151.2