Aion-RP 1.0 (8B)
🧠 AI Modelaion-labs
Top-ranked roleplaying model based on Llama 3.1 8B, excels in character evaluation benchmarks.
Aion-RP-Llama-3.1-8B is a fine-tuned base model derived from Llama 3.1 8B, specifically optimized for roleplaying tasks. It ranks highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto where LLMs evaluate each other's responses. The model supports a context length of 32,768 tokens and is available via OpenRouter with pricing at $0.80/M input tokens and $1.60/M output tokens. It features configurable parameters such as max_tokens, temperature, and top_p.
💡Highlights
- ├─Highest RPBench-Auto score
- ├─8B parameters
- └─32K context length
🎯For
- ├─Roleplaying enthusiasts
- ├─AI researchers
- └─Application developers