List your company

Reasoning on BOOTCAMP-EVAL

60.2Graphical PuzzlesQwen2.5-32B-Instruct
11.52824.16436.849.436Aug 12, 2025

Evaluation results

MethodLinks
Qwen2.5-32B-Instructtraining=Bootcamp-SFT2025.0860.255.461.55660.387.756.669.361.1
Qwen2.5-32B-Instructtraining=Bootcamp-SFT-RL2025.0852.461.364.147.563.787.544.477.359.5
Qwen3-235B-A22B2025.0849.555.854.55456.981.349.156.354.5
DeepSeek-R1-05282025.0847.246.650.961.15775.745.867.751
Qwen3-32B2025.0845.953.753.745.856.481.551.539.752.1
QwQ-32B2025.0845.253.856.737.660.472.542.344.751.4
DS-R1-Distilled-Qwen-32Btraining=Bootcamp-RL2025.0841.861.370.436.770.680.845.15255.7
DeepSeek-V3-03242025.083357.450.436.250.775.246.83746.5
DS-R1-Distilled-Qwen-32B2025.0831.520.349.825.432.85227.72531.5
Qwen2.5-32B-Instructtraining=Bootcamp-RL2025.0825.760.167.418.536.859.548.47246.9
Qwen2.5-32B-Instruct2025.0813.430.443.312.410.924.229.91024.4