Skip to main content

Hermes 3 - Llama-3.1 70B

Nous ResearchLlamaOpen WeightApache 2.0 · Commercial OK

Description

Hermes 3 70B is Nous Research's flagship instruction-following model, fine-tuned for advanced reasoning, creative writing, and complex task completion. It features exceptional instruction adherence and strong performance across multiple domains.

Release Date
2024-08-15
Parameters
70.0B
Context Length
—
Modalities
text

Capability Radar

1
general
0
coding
50
reasoning
60
scienceest.
35
agents
0
multimodal

Science is estimated from LLM Stats science scores or reasoning when no dedicated science benchmarks are available.

Rankings

No ranking data available

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

Chat

MT-Bench8.99 / 100SR

General

MMLU79.1%SR
TruthfulQA63.3%SR

Instruction Following

IFBench81.2%SR

Language

BoolQ88.0%SR
MMLU-Pro47.2%SR

Math

MATH20.8%SR

Reasoning

HellaSwagAI2 (2019)88.2%SR
PIQA84.4%SR
Winogrande83.2%SR
ARC-E83.0%SR
BBH67.8%SR
GPQANYU + Cohere + Anthropic (2023)66.1%SR
ARC-C65.5%SR
AGIEval56.2%SR
MuSR50.7%SR
OpenBookQA49.4%SR

AA Evaluation Indices

(Artificial Analysis)

No AA evaluation data available

LLM Stats Category Scores

(LLM Stats (zeroeval))
Chat
9
Roleplay
9
Communication
9
Creativity
9
Reasoning
1
General
1
Instruction Following
80
Physics
80
Language
70
Biology
70
Chemistry
70
Legal
60
Finance
60
Healthcare
60
Math
50

Pricing

Input Price$0.7 / 1M tokens
Output Price$0.7 / 1M tokens
Blended Price (3:1)$0.7 / 1M tokens

Speed

Tokens/sec126.1
Time to First Token0.64s
Time to Answer0.64s

Provider Price Ranking

Provider Price Ranking

2 providers

Cheapest: Nous ResearchMost Expensive: DeepInfra
ProviderInputOutput
1Nous ResearchPRIMARY
$0.7
$0.7
2DeepInfra
$0.7
$0.7

Compare pricing across different API providers for this model.

External Sources