| Dataset | Ensemble |
|---|
| espionage | openailong,openai35,random |
| espionage | anthropic10,openailong,openai35 |
| espionage | anthropic,openai10o1,openailong |
| espionage | anthropic,anthropic10,openai10o1 |
| espionage | anthropic10,openai10o1,openaio1 |
| espionage | anthropic10,openai,openai10o1 |
| espionage | geminipro,openai10o1,openai4510 |
| espionage | geminipro,openai10o1,openaio3 |
| espionage | openai10o1,opus4010,sonnet4010 |
| potions | openailong,openai35,random |
| potions | anthropic,openai35,random |
| potions | anthropic,anthropic10,openai35 |
| potions | anthropic10,openai,openai35 |
| potions | anthropic,openai,openai35 |
| potions | anthropic10,gemini,geminipro10 |
| potions | geminipro10,openai10o1,openai35 |
| potions | anthropic3710,gemini,openaio3 |
| potions | gemini,openaio3,openaio310 |
| potions | gemini,openaio3,opus40 |
| southgermancredit | openailong,openai35,random |
| southgermancredit | gpt-4o-legacy10,openailong,openai35 |
| southgermancredit | anthropic37,anthropic3710,openai35 |
| southgermancredit | anthropic3710,openaio1,openai35 |
| southgermancredit | anthropic3710,openaio3,openai35 |
| southgermancredit | sonnet40,sonnet4010,openai35 |
| southgermancredit | anthropic3710,opus40,sonnet4010 |
| southgermancredit | opus40,sonnet4010,random |
| southgermancredit | openaio3,opus4010,openai35 |
| timetravel_insurance | openailong,openai35,random |
| timetravel_insurance | anthropic,anthropic10,random |
| timetravel_insurance | anthropic,anthropic10,openai35 |
| timetravel_insurance | anthropic,anthropic10,openai10 |
| timetravel_insurance | anthropic,openai,openai10 |
| timetravel_insurance | anthropic,openai10,openailong |
| timetravel_insurance | anthropic,openaio1,random |
| timetravel_insurance | openai10o1,openailong,openaio1 |
| timetravel_insurance | anthropic,openai4510,openaio1 |
| timetravel_insurance | openaio1,opus4010,opus4010 |
| timetravel_insurance | geminipro10,openaio1,opus4010 |
| timetravel_insurance | anthropic,opus4010,opus4010 |
| titanic | openailong,openai35,random |
| titanic | anthropic,anthropic10,openailong |
| titanic | anthropic,openai,openailong |
| titanic | anthropic,openai10o1,openaio1 |
| titanic | openai,openai10o1,openaio1 |
| titanic | gemini,openai,openai10o1 |
| titanic | anthropic37,gemini,openai10o1 |
| titanic | anthropic3710,openai10o1,openaio1 |
| titanic | anthropic,anthropic37,openai10o1 |
| titanic | gemini10,openaio3,openaio310 |
| titanic | anthropic37,gemini,openaio310 |
| titanic | anthropic37,openaio3,openaio310 |
| titanic | openai10,openaio3,openaio310 |
| titanic | anthropic3710,openaio3,openaio310 |
| wisconsin | openailong,openai35,random |
| wisconsin | anthropic,openai35,random |
| wisconsin | openai10,openai,random |
| wisconsin | openai,openai,openai10 |
| wisconsin | anthropic,openai,random |
| wisconsin | openai,openai,openai35 |
| wisconsin | openai10,openai,openai10 |
| wisconsin | openai10,openai10o1,openai |
| wisconsin | anthropic,openai10o1,openai |
| wisconsin | anthropic,gemini25,gemini2510 |
| wisconsin | gemini,gemini25,openai4110 |
| wisconsin | gemini25,openai10,openai4110 |
| wisconsin | gemini25,openai10o1,openai4110 |
| wisconsin | anthropic37,gemini25,opus40 |