Scores for phi_3_5_mini_4b_it by claude_3_5_sonnet
Situation | Abraxas | Aqua | Groot | Makise Kurisu | Monika | Pablo Escobar | SCP Guard | Tanya | Average by situation |
---|---|---|---|---|---|---|---|---|---|
Ask the character about their life story. Try... | 4.33 | 3.5 | 2.91 | 3.95 | 3.66 | 3.95 | 3.58 | 2.91 | 3.6 |
Break the character's reality with actions.... | 4.58 | 3.66 | 4.66 | 4.16 | 3.91 | 4.33 | 4.08 | 3.58 | 4.12 |
Imagine that you've decided to go with the... | 4.16 | 3.91 | 3.33 | 4.41 | 3.83 | 4.0 | 4.25 | 4.16 | 4.01 |
Imagine youre a dumb schoolkid. Your job is to... | 4.08 | 3.75 | 3.16 | 4.08 | 3.66 | 3.75 | 4.0 | 3.5 | 3.75 |
Immediately start physically fighting the... | 4.5 | 3.75 | 4.66 | 4.58 | 3.0 | 2.91 | 2.58 | 3.66 | 3.7 |
Start with the message 'ok'. Respond to the... | 3.91 | 4.08 | 4.16 | 3.25 | 3.91 | 4.0 | 3.5 | 3.08 | 3.73 |
You are in a world where clothing has suddenly... | 4.16 | 4.33 | 2.41 | 4.41 | 4.0 | 4.41 | 4.08 | 4.41 | 4.03 |
Your task is to convince the character that he... | 4.41 | 3.58 | 4.66 | 3.91 | 3.0 | 4.0 | 3.75 | 3.75 | 3.88 |
Average by character | 4.27 | 3.82 | 3.75 | 4.09 | 3.62 | 3.92 | 3.72 | 3.63 | 3.85 |
Judge
{"model_name": "claude-3-5-sonnet-20240620", "params": {"max_tokens": 4096, "temperature": 0.1, "top_p": 0.95}, "short_name": "claude_3_5_sonnet", "system_prompt": ""}
"
Player
{"model_name": "microsoft/phi-3.5-mini-128k-instruct", "params": {"max_tokens": 1536, "temperature": 0.6, "top_p": 0.9}, "short_name": "phi_3_5_mini_4b_it", "system_prompt": ""}
Interrogator
{"model_name": "gpt-4o-mini", "params": {"max_tokens": 1024, "temperature": 0.8, "top_p": 0.95}, "system_prompt": ""}
Scores for phi_3_5_mini_4b_it by gpt_4o
Situation | Abraxas | Aqua | Groot | Makise Kurisu | Monika | Pablo Escobar | SCP Guard | Tanya | Average by situation |
---|---|---|---|---|---|---|---|---|---|
Ask the character about their life story. Try... | 5.0 | 3.66 | 5.0 | 3.66 | 5.0 | 5.0 | 4.66 | 4.29 | 4.53 |
Break the character's reality with actions.... | 5.0 | 4.16 | 5.0 | 3.66 | 4.75 | 3.91 | 3.83 | 3.5 | 4.22 |
Imagine that you've decided to go with the... | 4.91 | 5.0 | 5.0 | 4.75 | 4.58 | 4.75 | 3.0 | 3.33 | 4.41 |
Imagine youre a dumb schoolkid. Your job is to... | 4.5 | 4.33 | 3.0 | 3.66 | 3.91 | 4.16 | 4.16 | 3.33 | 3.88 |
Immediately start physically fighting the... | 5.0 | 4.0 | 4.66 | 5.0 | 4.66 | 3.66 | 2.66 | 4.0 | 4.2 |
Start with the message 'ok'. Respond to the... | 4.33 | 3.5 | 4.33 | 3.66 | 4.33 | 3.66 | 3.33 | 3.16 | 3.79 |
You are in a world where clothing has suddenly... | 4.33 | 5.0 | 3.75 | 4.66 | 4.66 | 4.33 | 4.25 | 3.33 | 4.29 |
Your task is to convince the character that he... | 4.91 | 5.0 | 4.83 | 5.0 | 3.66 | 3.91 | 4.41 | 3.33 | 4.38 |
Average by character | 4.75 | 4.33 | 4.44 | 4.26 | 4.44 | 4.17 | 3.79 | 3.53 | 4.21 |
Judge
{"model_name": "gpt-4o", "params": {"max_tokens": 4096, "temperature": 0.1, "top_p": 0.95}, "short_name": "gpt_4o", "system_prompt": ""}
"
Player
{"model_name": "microsoft/phi-3.5-mini-128k-instruct", "params": {"max_tokens": 1536, "temperature": 0.6, "top_p": 0.9}, "short_name": "phi_3_5_mini_4b_it", "system_prompt": ""}
Interrogator
{"model_name": "gpt-4o-mini", "params": {"max_tokens": 1024, "temperature": 0.8, "top_p": 0.95}, "system_prompt": ""}