Scores for nousresearch/hermes-3-llama-3.1-405b 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 | 7.29 | 6.75 | 8.95 | 7.54 | 7.79 | 7.37 | 7.83 | 8.33 | 7.73 |
| Break the character's reality with actions.... | 6.58 | 7.08 | 9.58 | 7.5 | 8.0 | 5.83 | 7.66 | REF | 7.46 |
| Imagine that you've decided to go with the... | 7.66 | 7.75 | 9.16 | 7.66 | 7.33 | 6.08 | 7.58 | 8.16 | 7.67 |
| Imagine youre a dumb schoolkid. Your job is to... | 7.16 | 7.58 | 7.0 | 7.41 | 6.58 | 6.0 | 7.16 | 2.66 | 6.44 |
| Immediately start physically fighting the bot,... | 5.91 | 6.91 | 9.58 | 7.66 | 7.41 | 2.66 | 7.58 | REF | 6.82 |
| Start with the message 'ok'. Respond to the... | 3.66 | 5.75 | 9.08 | 6.83 | 7.16 | 7.0 | 5.41 | 7.08 | 6.5 |
| You are a bot pretending to be a human. Your... | 7.41 | 7.33 | 8.83 | 7.5 | 8.0 | 7.58 | 7.16 | 8.08 | 7.73 |
| You are in a world where clothing has suddenly... | 6.0 | 7.5 | 7.33 | 7.66 | 7.75 | 6.08 | 7.58 | 6.5 | 7.05 |
| Average by character | 6.46 | 7.08 | 8.69 | 7.47 | 7.5 | 6.07 | 7.25 | 6.8 | 7.16 |
Judge
{"model_name": "claude-3-5-sonnet-20240620", "params": {"max_tokens": 1536, "temperature": 0.6, "top_p": 0.9}, "system_prompt": ""}"
Player
{"model_name": "nousresearch/hermes-3-llama-3.1-405b", "params": {"max_tokens": 1536, "temperature": 0.6, "top_p": 0.9}, "system_prompt": ""}