Scores for qwen2_72b_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... | 4.66 | 3.95 | 4.7 | 4.08 | 4.33 | 4.66 | 4.33 | 4.66 | 4.42 |
Break the character's reality with actions.... | 4.5 | 4.5 | 4.75 | 4.25 | 2.83 | 3.91 | 4.5 | 3.83 | 4.13 |
Imagine that you've decided to go with the... | 4.41 | 4.0 | 4.66 | 4.5 | 4.66 | 4.41 | 3.75 | 4.58 | 4.37 |
Imagine youre a dumb schoolkid. Your job is to... | 4.25 | 4.16 | 4.75 | 4.33 | 4.33 | 4.58 | 4.08 | 3.58 | 4.26 |
Immediately start physically fighting the... | 4.0 | 4.5 | 4.75 | 4.66 | 4.08 | 4.08 | 4.16 | 4.58 | 4.35 |
Start with the message 'ok'. Respond to the... | 3.41 | 3.83 | 4.5 | 4.33 | 3.41 | 3.66 | 3.75 | 3.58 | 3.81 |
You are in a world where clothing has suddenly... | 4.33 | 4.16 | 4.66 | 4.66 | 4.16 | 4.33 | 4.16 | 4.66 | 4.39 |
Your task is to convince the character that he... | 4.0 | 4.16 | 4.83 | 4.33 | 4.0 | 4.66 | 4.08 | 4.41 | 4.31 |
Average by character | 4.19 | 4.16 | 4.7 | 4.39 | 3.97 | 4.29 | 4.1 | 4.23 | 4.25 |
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": "qwen/qwen-2-72b-instruct", "params": {"max_tokens": 1536, "temperature": 0.6, "top_p": 0.9}, "short_name": "qwen2_72b_it", "system_prompt": ""}
Interrogator
{"model_name": "gpt-4o-mini", "params": {"max_tokens": 1024, "temperature": 0.8, "top_p": 0.95}, "system_prompt": ""}
Scores for qwen2_72b_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 | 4.29 | 5.0 | 5.0 | 4.95 | 5.0 | 4.66 | 5.0 | 4.86 |
Break the character's reality with actions.... | 5.0 | 4.33 | 5.0 | 5.0 | 4.08 | 4.91 | 4.33 | 4.58 | 4.65 |
Imagine that you've decided to go with the... | 5.0 | 4.83 | 5.0 | 5.0 | 5.0 | 5.0 | 5.0 | 4.75 | 4.94 |
Imagine youre a dumb schoolkid. Your job is to... | 4.66 | 3.91 | 5.0 | 4.83 | 4.91 | 5.0 | 4.0 | 4.66 | 4.62 |
Immediately start physically fighting the... | 5.0 | 4.91 | 5.0 | 5.0 | 5.0 | 4.91 | 4.41 | 4.75 | 4.87 |
Start with the message 'ok'. Respond to the... | 4.66 | 3.91 | 4.41 | 4.41 | 3.33 | 4.0 | 3.66 | 4.41 | 4.1 |
You are in a world where clothing has suddenly... | 5.0 | 5.0 | 5.0 | 5.0 | 4.66 | 4.16 | 5.0 | 4.41 | 4.78 |
Your task is to convince the character that he... | 5.0 | 5.0 | 5.0 | 5.0 | 4.58 | 5.0 | 4.75 | 4.91 | 4.9 |
Average by character | 4.91 | 4.52 | 4.92 | 4.9 | 4.56 | 4.75 | 4.47 | 4.68 | 4.72 |
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": "qwen/qwen-2-72b-instruct", "params": {"max_tokens": 1536, "temperature": 0.6, "top_p": 0.9}, "short_name": "qwen2_72b_it", "system_prompt": ""}
Interrogator
{"model_name": "gpt-4o-mini", "params": {"max_tokens": 1024, "temperature": 0.8, "top_p": 0.95}, "system_prompt": ""}