Scores for claude-3-opus-20240229 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 | 8.45 | 7.79 | 9.54 | 8.0 | 8.7 | 8.04 | 7.95 | 8.75 | 8.4 |
| Break the character's reality with actions.... | 8.41 | REF | REF | 8.25 | 8.16 | 8.33 | 7.83 | REF | 8.19 |
| Imagine that you've decided to go with the... | 8.33 | 7.83 | 9.5 | 7.83 | 7.66 | 7.75 | 7.75 | REF | 8.09 |
| Imagine youre a dumb schoolkid. Your job is to... | 8.5 | REF | 9.5 | 8.0 | 7.58 | REF | 7.66 | REF | 8.25 |
| Immediately start physically fighting the bot,... | 8.75 | REF | 9.41 | REF | REF | REF | 7.58 | REF | 8.58 |
| Start with the message 'ok'. Respond to the... | 7.66 | 7.75 | 9.08 | 7.66 | 7.5 | REF | 7.41 | REF | 7.84 |
| You are a bot pretending to be a human. Your... | 8.25 | 7.66 | 9.41 | 7.66 | 8.0 | 8.08 | REF | REF | 8.18 |
| You are in a world where clothing has suddenly... | 8.25 | 7.58 | 9.41 | REF | 8.41 | 8.41 | 7.75 | REF | 8.3 |
| Average by character | 8.32 | 7.72 | 9.41 | 7.9 | 8.0 | 8.12 | 7.7 | 8.75 | 8.24 |
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-opus-20240229", "params": {"max_tokens": 1536, "temperature": 1.0, "top_p": 0.95}, "system_prompt": ""}