How much does Hermes 2 Pro - Llama-3 8B cost?

Hermes 2 Pro - Llama-3 8B costs $0.14 per million input tokens and $0.14 per million output tokens. For a typical conversation (~2,000 tokens), that's approximately $0.000 per message.

What benchmarks has Hermes 2 Pro - Llama-3 8B been tested on?

Hermes 2 Pro - Llama-3 8B has been evaluated on 6 benchmarks. Top scores: IFEval: 53.6, BBH (HuggingFace): 30.7, MMLU-PRO: 22.8.

Is Hermes 2 Pro - Llama-3 8B open source?

Yes, Hermes 2 Pro - Llama-3 8B is open source.

How does Hermes 2 Pro - Llama-3 8B compare to Command R+ (08-2024)?

Hermes 2 Pro - Llama-3 8B has an average score of 38.2 while Command R+ (08-2024) scores 38.3. Command R+ (08-2024) slightly outperforms Hermes 2 Pro - Llama-3 8B overall. Hermes 2 Pro - Llama-3 8B costs $0.14/1M input vs Command R+ (08-2024) at $2.50/1M input. See full comparison →

Home/Models/Hermes 2 Pro - Llama-3 8B

Hermes 2 Pro - Llama-3 8B

Name: Hermes 2 Pro - Llama-3 8B
Price: 0.14 USD
Author: nousresearch

by nousresearch · Released May 2024

Open Source

38.2

avg score

Rank #152

Compare

Better than 35% of all models

Context

8K tokens (~4 books)

Input $/1M

$0.14

Output $/1M

$0.14

Type

text

License

Open Source

Benchmarks

6 tested

Data updated today

About

Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced...

Tested on 6 benchmarks with 22.1% average. Top scores: IFEval (53.6%), BBH (HuggingFace) (30.7%), MMLU-PRO (22.8%).

Looking for similar performance at lower cost?
GLM 4 32B scores 37.8 (99% as good) at $0.10/1M input · 29% cheaper

Capabilities

reasoning

11.3

#128 globally

math

8.4

#190 globally

knowledge

14.3

#205 globally

language

53.6

#101 globally

general

30.7

#29 globally

Benchmark Scores

Compare All

Tested on 6 benchmarks · Ranked across 5 categories

Score Distribution (all 233 models)

0255075100

▲ You are here

reasoningCompare reasoning →

MUSR

HuggingFace MuSR (Multi-Step Reasoning). Tests multi-hop reasoning requiring chaining multiple facts together.

11.3—

mathCompare math →

MATH Level 5

HuggingFace evaluation of MATH Level 5 problems. Competition math requiring advanced reasoning and proof construction.

8.4—

knowledgeCompare knowledge →

MMLU-PRO

HuggingFace MMLU-Pro. Harder version of MMLU with 10 answer choices instead of 4 and more challenging questions.

22.8—

GPQA

HuggingFace evaluation of GPQA (Graduate-Level Google-Proof Q&A). PhD-level science questions that cannot be easily searched.

5.7—

Quick compare:

vs Command R+ (08-2024)

vs DeepSeek R1 Distill Qwen 7B

vs Gemini 2.5 Flash

Excellent (85+) Good (70-85) Average (50-70) Below (<50)

Similar Models

Command R+ (08-2024)

Cohere

38.3$2.50/1M

DeepSeek R1 Distill Qwen 7B

Links

Info

nousresearch Pricing explorer Developers · API

Research

Documentation

Community

Source Code

BenchGecko API

hermes-2-pro-llama-3-8b

Specifications

Typetext
Context8K tokens (~4 books)
ReleasedMay 2024
LicenseOpen Source
StatusActive
Cost / Message~$0.000

Available On

nousresearch$0.14

Frequently Asked Questions

Hermes 2 Pro - Llama-3 8B is an open-source text AI model by nousresearch, released in May 2024. It has an average benchmark score of 38.2. Context window: 8K tokens.

Benchmarks

IFEval BBH (HuggingFace)MMLU-PRO MUSR MATH Level 5

nousresearch · Provider nousresearch · Economy All Models Compare Models Pricing Developers · API

Hermes 2 Pro - Llama-3 8B

Frequently Asked Questions

Related Models

Benchmarks

Related Pages