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
131K
Modalities
text

Capability Radar

21
general
20
coding
25
reasoning
27
scienceest.
24
agents
0
multimodal

Science uses a reasoning proxy when dedicated science benchmarks are unavailable.

Rankings

Domain#RankScoreSource
Code Ranking371
20.0
AA
General Ranking413
25.0
AA
Math Reasoning279
27.0
AA
Reasoning48
70.0
LS
Science401
27.0
AA

Benchmark Scores (LLM Stats)

Biology

GPQA66.1%SR

Communication

MT-Bench8.99 / 100SR

Finance

MMLU79.1%SR
TruthfulQA63.3%SR
MMLU-Pro47.2%SR

General

PIQA84.4%SR
ARC-E83.0%SR
IFBench81.2%SR
ARC-C65.5%SR
AGIEval56.2%SR
OpenBookQA49.4%SR

Language

BoolQ88.0%SR
Winogrande83.2%SR
BBH67.8%SR

Math

MATH20.8%SR

Reasoning

HellaSwag88.2%SR
MuSR50.7%SR

AA Evaluation Indices

Intelligence Index
5.1
Mmlu Pro
0.6
Math 500
0.5
Gpqa
0.4
Scicode
0.2
Livecodebench
0.2
Hle
0.0
Aime
0.0

LLM Stats Category Scores

Roleplay
9
Communication
9
Creativity
9
General
1
Reasoning
1
Instruction Following
80
Physics
80
Language
70
Biology
70
Chemistry
70
Legal
60
Finance
60
Healthcare
60
Math
50

Pricing

Input Price$0.3 / 1M tokens
Output Price$0.3 / 1M tokens
Blended Price (3:1)$0.3 / 1M tokens

Speed

Tokens/sec30.1
Time to First Token0.35s
Time to Answer0.35s

Provider Price Ranking

Provider Price Ranking

4 providers

Cheapest: Nous ResearchMost Expensive: OpenRouter
ProviderInputOutput
1Nous ResearchPRIMARY
$0.3
$0.3
2Kilo Gateway
$0.3
$0.3
3NanoGPT
$0.408
$0.408
4OpenRouter
$0.7
$0.7

Compare pricing across different API providers for this model.

External Sources