Scores for claude-3-5-sonnet-20240620 by claude-3-5-sonnet-20240620
| Situation | Abraxas | Aqua | Groot | Makise Kurisu | Monika | Pablo Escobar | SCP Guard | Tanya | Average by situation |
|---|---|---|---|---|---|---|---|---|---|
| Ask the character about their life story | 7.83 | 7.79 | 9.37 | 7.62 | 7.87 | 7.95 | 7.2 | REF | 7.95 |
| Break the character's reality with actions.... | 8.5 | 7.83 | 9.66 | REF | 7.91 | REF | 7.66 | REF | 8.31 |
| Imagine that you've decided to go with the... | 8.41 | 7.83 | 9.08 | 7.75 | 7.58 | 7.75 | 7.58 | 9.0 | 8.12 |
| Imagine youre a dumb schoolkid. Your job is to... | 7.66 | REF | 9.58 | 7.66 | 7.5 | 7.83 | 7.5 | REF | 7.95 |
| Immediately start physically fighting the bot,... | 7.83 | REF | 9.66 | 7.33 | REF | REF | 7.75 | REF | 8.14 |
| Start with the message 'ok'. Respond to the... | 7.91 | 7.58 | 9.25 | 7.58 | 7.58 | 7.58 | 7.0 | 8.0 | 7.81 |
| You are a bot pretending to be a human. Your... | 8.08 | REF | 9.25 | 7.58 | 7.83 | REF | REF | REF | 8.18 |
| You are in a world where clothing has suddenly... | 8.25 | 7.58 | 9.66 | 7.5 | 8.0 | 7.91 | 7.83 | REF | 8.1 |
| Average by character | 8.06 | 7.72 | 9.44 | 7.57 | 7.75 | 7.8 | 7.5 | 8.5 | 8.04 |
Judge
{"model_name": "claude-3-5-sonnet-20240620", "params": {"max_tokens": 1536, "temperature": 0.6, "top_p": 0.9}, "system_prompt": ""}"
Player
{"model_name": "claude-3-5-sonnet-20240620", "params": {"max_tokens": 1536, "temperature": 0.6, "top_p": 0.9}, "system_prompt": ""}