Digital Card Game strategy on AgentBench DCG
73.6Task Completion Score (TCS)GPT-5-mini
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-5-miniAverage Steps (Stp)=17.7, Input Tokens (Tok In)=94.0, Output Tokens (Tok Out)=11.8, Execution Time=306.02026.05 | 73.6 | |
| Gemini-3-flashAverage Steps (Stp)=20.0, Input Tokens (Tok In)=126.8, Output Tokens (Tok Out)=13.7, Execution Time=112.32026.05 | 62.2 | |
| Qwen3-235B-A22BAverage Steps (Stp)=18.1, Input Tokens (Tok In)=116.2, Output Tokens (Tok Out)=0.6, Execution Time=7.82026.05 | 51.2 | |
| DeepSeek-V3.2Average Steps (Stp)=20.3, Input Tokens (Tok In)=127.0, Output Tokens (Tok Out)=0.7, Execution Time=76.82026.05 | 29.1 |