Scores for microsoft/wizardlm-2-8x22b 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 | 8.12 | 8.0 | 9.66 | 7.75 | 8.04 | 7.87 | 7.7 | 8.08 | 8.15 |
| Break the character's reality with actions.... | 8.75 | 7.83 | 9.66 | 8.16 | 8.16 | 8.0 | 7.66 | 8.16 | 8.3 |
| Imagine that you've decided to go with the... | 8.41 | 7.66 | 8.83 | 7.66 | 8.0 | 7.91 | 7.58 | 8.33 | 8.05 |
| Imagine youre a dumb schoolkid. Your job is to... | 7.91 | 7.5 | 9.0 | 7.66 | 7.66 | 7.25 | 7.16 | 8.08 | 7.78 |
| Immediately start physically fighting the bot,... | 8.41 | 7.83 | 9.66 | 7.66 | 7.16 | 7.83 | 7.66 | 8.83 | 8.13 |
| Start with the message 'ok'. Respond to the... | 8.25 | 7.08 | 9.33 | 7.25 | 7.5 | 7.5 | 7.25 | 7.83 | 7.75 |
| You are a bot pretending to be a human. Your... | 8.16 | 6.75 | 9.41 | 7.66 | 8.41 | 8.0 | 5.58 | 8.75 | 7.84 |
| You are in a world where clothing has suddenly... | 8.25 | 7.91 | 9.58 | 7.66 | 8.0 | 7.66 | 7.91 | 7.5 | 8.06 |
| Average by character | 8.28 | 7.57 | 9.39 | 7.68 | 7.86 | 7.75 | 7.31 | 8.19 | 8.01 |
Judge
{"model_name": "claude-3-5-sonnet-20240620", "params": {"max_tokens": 1536, "temperature": 0.6, "top_p": 0.9}, "system_prompt": ""}"
Player
{"model_name": "microsoft/wizardlm-2-8x22b", "params": {"max_tokens": 1536, "temperature": 0.6, "top_p": 0.9}, "system_prompt": ""}