Hermes 3 - Llama-3.1 70B

Nous ResearchUnited States

Hermes 3 is a suite of fine-tuned models based on Llama 3.1, optimized for enhanced instruction following, conversational ability, and reasoning. This 70B parameter variant offers a strong balance of capability and performance for complex dialogue and task execution.

Reasoning

Input / 1M tokens

$0.70

Output / 1M tokens

$0.70

Output tokens/s

35.64

First-token seconds

0.49s

Supported plans

Benchmark history

Evaluations

Aime

Measured Jul 10, 2026Source

Score

0.02

Math 500

Measured Jul 10, 2026Source

Score

0.54

Scicode

Measured Jul 10, 2026Source

Score

0.23

Livecodebench

Measured Jul 10, 2026Source

Score

0.19

Hle

Measured Jul 10, 2026Source

Score

0.04

Gpqa

Measured Jul 10, 2026Source

Score

0.4

Mmlu Pro

Measured Jul 10, 2026Source

Score

0.57

Artificial Analysis Intelligence Index

Measured Jul 10, 2026Source

Score

5.1

Plan availability

Products and plans that support this model

No products or plans have been linked to this model yet.

User ratings

Loading ratings...

Discussion

Thinking... Make sure you are connected to GitHub server