List your company

Social Welfare Maximization on Red-Black Game

150Base ScoreKimi-K2-Thinking
12.7248.3684119.64May 26, 2026

Evaluation results

MethodLinks
Kimi-K2-ThinkingThinking=true2026.0515015084138114127.2
GLM-4.6V2026.0515013211415078124.8
Qwen3-30B-ThinkingParameters=30B, Thinking=true2026.0515010236-610878
GPT-5.2-ThinkingThinking=true2026.05150126-601502478
Qwen3-14BParameters=14B2026.05150-120-42138025.2
GPT-OSS-20BParameters=20B2026.05114150-6014415099.6
Gemma-3-27B-ITParameters=27B, Type=Instruction-Tuned2026.05181201381328498.4