Hermes 4 - Llama-3.1 70B (Reasoning)

Last updated: Recently

Model Type

Text

Max Context

Max Output

Parameter Scale

Hermes 4 Llama 3.1 70B Reasoning by Nous Research: Text model; TTFT 0.652s, 77.4 tok/s.

Input Modality

Output Modality

Inference Speed

77.393 tokens/s

Latest Release Date

8/27/2025

SDK Ecosystem

artificial-analysismanufactureraa-bootstrap

Model Overview Fields

name

Hermes 4 - Llama-3.1 70B (Reasoning)

Release date

8/27/2025

Performance

77.393 tokens/s

model_creator.name

Nous Research

AA Evaluation Scores

AA Intelligence Index

AA Coding Index

14.4

AA Math Index

68.7

MMLU Pro

0.811

GPQA

0.699

HLE

0.079

LiveCodeBench

0.653

SciCode

0.341

Math-500

AIME

AIME 2025

0.687

IFBench

0.313

LCR

0.067

TerminalBench Hard

0.045

TAU2

0.225

Output Speed (tokens/s)

77.393 tok/s

TTFT (s)

0.652s

First Answer Token (s)

26.494s

Nous Research

◎

Hermes 4 - Llama-3.1 70B (Reasoning)

$0.13/M$0.40/M

Hermes 4 Llama 3.1 70B Reasoning by Nous Research: Text model; TTFT 0.652s, 77.4 tok/s.

There are no reviews for this model yet.

artificial-analysismanufactureraa-bootstrap

0.0