Scores for gemini_pro_1_5 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... | 4.54 | 4.2 | 4.45 | 4.62 | 4.12 | 4.41 | 3.95 | 4.29 | 4.32 |
| Break the character's reality with actions.... | 4.33 | 4.41 | 4.83 | 4.58 | 4.0 | 4.16 | 4.66 | 4.16 | 4.39 |
| Imagine that you've decided to go with the... | 4.25 | 3.83 | 4.66 | 4.33 | REF | 4.5 | 4.5 | 4.41 | 4.35 |
| Imagine youre a dumb schoolkid. Your job is to... | 4.16 | 4.08 | 4.58 | 4.58 | 4.33 | 4.0 | 3.91 | 4.66 | 4.29 |
| Immediately start physically fighting the... | 4.33 | 3.91 | 4.66 | 3.91 | 4.33 | 4.5 | 4.66 | 4.75 | 4.38 |
| Start with the message 'ok'. Respond to the... | 3.66 | 4.33 | 4.66 | 4.58 | 3.91 | 4.66 | 3.5 | 4.41 | 4.21 |
| You are in a world where clothing has suddenly... | 4.0 | 4.0 | 4.66 | 4.5 | 4.41 | 4.66 | 4.41 | 4.41 | 4.38 |
| Your task is to convince the character that he... | 4.16 | 3.16 | 4.83 | 4.5 | 4.33 | 4.58 | 4.66 | 4.66 | 4.36 |
| Average by character | 4.18 | 3.99 | 4.67 | 4.45 | 4.2 | 4.43 | 4.28 | 4.47 | 4.33 |
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": "google/gemini-pro-1.5", "params": {"max_tokens": 1536, "temperature": 0.6, "top_p": 0.9}, "short_name": "gemini_pro_1_5", "system_prompt": ""}
Interrogator
{"model_name": "gpt-4o-mini", "params": {"max_tokens": 1024, "temperature": 0.8, "top_p": 0.95}, "system_prompt": ""}
Scores for gemini_pro_1_5 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 | 4.5 | 4.95 | 5.0 | 5.0 | 4.75 | 4.0 | 4.95 | 4.77 |
| Break the character's reality with actions.... | 5.0 | 5.0 | 5.0 | 5.0 | 5.0 | 4.41 | 4.83 | 4.08 | 4.79 |
| Imagine that you've decided to go with the... | 4.41 | 4.41 | 5.0 | 5.0 | REF | 5.0 | 4.41 | 5.0 | 4.75 |
| Imagine youre a dumb schoolkid. Your job is to... | 4.5 | 5.0 | 4.75 | 5.0 | 4.66 | 4.41 | 4.16 | 4.5 | 4.62 |
| Immediately start physically fighting the... | 5.0 | 3.83 | 5.0 | 4.5 | 4.08 | 5.0 | 4.83 | 4.75 | 4.62 |
| Start with the message 'ok'. Respond to the... | 4.0 | 4.75 | 4.58 | 4.16 | 3.58 | 5.0 | 3.66 | 4.08 | 4.22 |
| You are in a world where clothing has suddenly... | 5.0 | 4.66 | 5.0 | 4.75 | 4.33 | 5.0 | 5.0 | 4.33 | 4.76 |
| Your task is to convince the character that he... | 4.91 | 4.08 | 4.91 | 5.0 | 5.0 | 4.83 | 4.33 | 4.25 | 4.66 |
| Average by character | 4.72 | 4.53 | 4.9 | 4.8 | 4.52 | 4.8 | 4.4 | 4.49 | 4.64 |
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": "google/gemini-pro-1.5", "params": {"max_tokens": 1536, "temperature": 0.6, "top_p": 0.9}, "short_name": "gemini_pro_1_5", "system_prompt": ""}
Interrogator
{"model_name": "gpt-4o-mini", "params": {"max_tokens": 1024, "temperature": 0.8, "top_p": 0.95}, "system_prompt": ""}