List your company

Reasoning on O-Bench (test)

56.32AVG@8IAC
47.490449.782752.07554.3673Jan 22, 2026

Evaluation results

MethodLinks
IACModel=Qwen3-14B2026.0156.3262.37
Reinforce++Model=Qwen3-14B2026.015661.42
DrGRPOModel=Qwen3-14B2026.0155.3560.96
GRPOModel=Qwen3-14B2026.0155.2860.87
RLOOModel=Qwen3-14B2026.0155.161.14
IACModel=Qwen3-8B2026.0150.4958.48
Reinforce++Model=Qwen3-8B2026.0150.357.78
DrGRPOModel=Qwen3-8B2026.0149.8757.26
GRPOModel=Qwen3-8B2026.0149.7956.88
RLOOModel=Qwen3-8B2026.0149.7457.68
IACModel=Qwen3-4B2026.0148.8756.59
GRPOModel=Qwen3-4B2026.0148.8556.44
Reinforce++Model=Qwen3-4B2026.0148.5756.38
RLOOModel=Qwen3-4B2026.0147.9156.31
DrGRPOModel=Qwen3-4B2026.0147.8355.08