AionLabs: Aion-RP 1.0 (8B)

by Aion Labstext->text1 endpoint
Neura Intelligence Index
4.0/ 100
Rank
#351
Confidence
high
Benchmarks
10(26% coverage)

Overview

Aion-RP-Llama-3.1-8B ranks the 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. It is a fine-tuned base model...

Capabilities

Text generation
Top-P sampling

Modalities

Input
Text
Output
Text

Technical Specifications

Context Window
32.8K tokens
Max Output
29.5K tokens
Knowledge Cutoff
2023-12-31
Tokenizer
Other
Uptime (24h)
10000.0%
Parameters
8B
Blended Cost
$0.06/1M tokens
License
llama-3.1Open Weights
Country
🇺🇸US
Model Family
Llama 3.1
Release Date
July 23, 20242y

Supported Parameters

max_tokenstemperaturetop_p

Benchmark Performance

general

BenchmarkScoreSource
Chatbot Arena Elo
1141
aggregated
IFEval
73.1
aggregated
MMLU-Pro
48.3
aggregated

coding

BenchmarkScoreSource
HumanEval
72.6
aggregated

math

BenchmarkScoreSource
GSM8K
84.5
aggregated
MATH
51.9
aggregated

reasoning

BenchmarkScoreSource
ARC-Challenge
83.4
aggregated

language

BenchmarkScoreSource
HellaSwag
82
aggregated
WinoGrande
78.9
aggregated

safety

BenchmarkScoreSource
TruthfulQA
52.4
aggregated

Performance Over Time

Pricing

Per 1M tokens
Input$0.80
Output$1.60
Added
February 4, 2025
Last synced 9/20/2026