NOUMENOpen app
NOUMEN

nousresearch · Open weights

Hermes 3 70B

Added Jan 7, 2026Open weights

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Use in the app

Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, better roleplaying, reasoning, multi-turn conversation, and long context coherence. This 70B model is a competitive finetune of Llama-3.1-70B focused on aligning LLMs to the user with powerful steering capabilities.

  • Tools
Input
Text
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.41
Output
$0.41

Reference prices as published by the model provider. API example

Specifications

Context window
65.5K
Max output
8.2K
Average output (7 days)
177 tokens
Longer than 18% of 468 models

Side by side

Hermes 3 70B compared

Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Hermes 3 70BnousresearchThis modelHermes 4 LargenousresearchRemove
Providernousresearchnousresearch
Discovery tierOpen weightsOpen weights
AddedJan 7, 2026Aug 26, 2025
Limits
Context window65.54K128KBest
Max output8.19K8.19K
Average output177 tokens199 tokens
Pricing, USD per 1M tokens
Input$0.41$0.30Best
Output$0.41Best$1.20
Performance
Throughput32.5 tok/s44.5 tok/sBest
Time to first token1.9 s0.7 sBest
Request success (24h)100.0%100.0%
Benchmark indexes
Intelligence Index6.07.4Best
Math Index—15.3
Capabilities
ToolsYesNo
Structured outputNoYes
Reasoning effort——

Public evaluations

Benchmarks

Independent evaluation results, with how each score ranks among the models in the Noumen catalog.

  • Hermes 3 70B
  • Hermes 4 Large

Intelligence Index

  • Hermes 3 70B6.0
  • Hermes 4 Large7.4

Hermes 3 70B: Better than 3% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Math Index

    Composite of the math evaluations

    • Hermes 3 70B: —
    • Hermes 4 Large: 15.3

Document reasoning

  • AA-LCRv1.1

    Reasoning across long documents

    • Hermes 3 70B: —
    • Hermes 4 Large: 22.0%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Hermes 3 70B: 4.0%
    • Hermes 4 Large: 4.2%Top

  • GPQA Diamond

    Graduate-level science questions

    • Hermes 3 70B: 40.1%
    • Hermes 4 Large: 53.6%Top

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • Hermes 3 70B: 57.1%
    • Hermes 4 Large: 72.9%Top

  • IFBench

    Following precise output instructions

    • Hermes 3 70B: —
    • Hermes 4 Large: 34.8%

Coding

  • LiveCodeBench

    Recent competitive programming problems

    • Hermes 3 70B: 18.8%
    • Hermes 4 Large: 54.6%Top

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • Hermes 3 70B: —
    • Hermes 4 Large: 15.3%

  • AIME

    Competition mathematics

    • Hermes 3 70B: 2.3%
    • Hermes 4 Large: —

  • MATH-500

    Competition math problems

    • Hermes 3 70B: 53.8%
    • Hermes 4 Large: —

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Hermes 3 70B: —
    • Hermes 4 Large: 9.8%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Hermes 3 70B: —
    • Hermes 4 Large: 26.6%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Hermes 3 70B: —
    • Hermes 4 Large: 22.0%

Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis

Live routing data

Performance and reliability

Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.

Throughput
32.5 tok/s
Faster than 22% of 263 models
Time to first token
1.9 s
Quicker than 84% of 263 models
Prompt cache hits
0.0%
Request success (24h)
100.0%
Reliable

Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.

Hourly request success · last 72 hoursLowest hour 100.0%
  • Healthy (98% or more)
  • Degraded (90–98%)
  • Down (under 90%)
  • No requests

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart
curl https://www.noumen.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $NOUMEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nousresearch/hermes-3-llama-3.1-70b",
    "messages": [{ "role": "user", "content": "Explain this stack trace." }]
  }'
import os
from openai import OpenAI

client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
    model="nousresearch/hermes-3-llama-3.1-70b",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

nousresearch

Other nousresearch models, starting with the same family.