Hermes 4 - Llama-3.1 405B (Non-reasoning)

Last updated: Recently

Model Type

Text

Max Context

Max Output

Parameter Scale

Hermes 4 Llama 3.1 405B Non reasoning by Nous Research: Text model; TTFT 0.744s, 33.7 tok/s.

Input Modality

Output Modality

Inference Speed

33.660 tokens/s

Latest Release Date

8/27/2025

SDK Ecosystem

artificial-analysismanufactureraa-bootstrap

Model Overview Fields

name

Hermes 4 - Llama-3.1 405B (Non-reasoning)

Release date

8/27/2025

Performance

33.660 tokens/s

model_creator.name

Nous Research

AA Evaluation Scores

AA Intelligence Index

17.6

AA Coding Index

18.1

AA Math Index

15.3

MMLU Pro

0.729

GPQA

0.536

HLE

0.042

LiveCodeBench

0.546

SciCode

0.346

Math-500

AIME

AIME 2025

0.153

IFBench

0.348

LCR

0.2

TerminalBench Hard

0.098

TAU2

0.266

Output Speed (tokens/s)

33.66 tok/s

TTFT (s)

0.744s

First Answer Token (s)

0.744s

Nous Research

◎

Hermes 4 - Llama-3.1 405B (Non-reasoning)

$1.00/M$3.00/M

Hermes 4 Llama 3.1 405B Non reasoning by Nous Research: Text model; TTFT 0.744s, 33.7 tok/s.

There are no reviews for this model yet.

artificial-analysismanufactureraa-bootstrap

0.0