AIbase
EN
Home
AI Models Finder
Hermes 3 Llama 3.1 70B
H

Hermes 3 Llama 3.1 70B

Hermes 3 model based on Llama 3.1 70B, significantly enhancing conversation and reasoning capabilities through high-quality instruction tuning. Inherits Llama 3.1's powerful base capabilities while excelling in instruction following, conversation quality, and complex task processing through Hermes series optimization. Suitable for high-quality conversational AI applications like intelligent assistants, customer service, and professional consulting systems.
Intelligence(Relatively Weak)
Speed(Slow)
Input Supported Modalities
Yes
Is Reasoning Model
128,000
Context Window
-
Maximum Output Tokens
-
Knowledge Cutoff
Go Compare

Pricing

- /M tokens
Input
- /M tokens
Output
- /M tokens
Blended Price

Quick Simple Comparison

Input

Output

Hermes 3 - Llama-3.1 70B
DeepHermes 3 - Llama-3.1 8B Preview
DeepHermes 3 - Mistral 24B Preview

Basic Parameters

Hermes 3 - Llama-3.1 70BTechnical Parameters
Parameter Count
Not Announced
Context Length
128.00k tokens
Training Data Cutoff
Open Source Category
Open Weights (Permissive License)
Multimodal Support
Text Only
Throughput
Release Date
2024-08-15
Response Speed
0 tokens/s

Benchmark Scores

Below is the performance of Hermes 3 - Llama-3.1 70B in various standard benchmark tests. These tests evaluate the model's capabilities in different tasks and domains.
Intelligence Index
29.14
Large Language Model Intelligence Level
Coding Index
20.99
Indicator of AI model performance on coding tasks
Math Index
28.07
Capability indicator in solving mathematical problems, mathematical reasoning, or performing math-related tasks
MMLU Pro
57.1
Massive Multitask Multimodal Understanding - Testing understanding of text, images, audio, and video
GPQA
40.1
Graduate Physics Questions Assessment - Testing advanced physics knowledge with diamond science-level questions
HLE
4.1
The model's comprehensive average score on the Hugging Face Open LLM Leaderboard
LiveCodeBench
18.8
Specific evaluation focused on assessing large language models' ability in real-world code writing and solving programming competition problems
SciCode
23.1
The model's capability in code generation for scientific computing or specific scientific domains
HumanEval
75.1
Score achieved by the AI model on the specific HumanEval benchmark test set
Math 500 Score
53.8
Score on the first 500 larger, more well-known mathematical benchmark tests
AIME Score
2.3
An indicator measuring an AI model's ability to solve high-difficulty mathematical competition problems (specifically AIME level)
AIbase
Empowering the Future, Your AI Solution Knowledge Base
English简体中文繁體中文にほんご
© 2025AIbase