NOUMENOpen app
NOUMEN

nousresearch · Open weights

Hermes 4 Large

Added Aug 26, 2025Open weights

Compare models

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

Loading models…

Use in the app

Advanced reasoning model built on Llama-3.1-405B with hybrid thinking modes. Features internal deliberation capabilities, excels at math, code, STEM, and logical reasoning while supporting structured outputs with improved steerability and neutral alignment.

  • Structured output
Input
Text
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.30
Output
$1.20

Reference prices as published by the model provider. API example

Specifications

Context window
128K
Max output
8.2K
Average output (7 days)
199 tokens
Longer than 21% of 468 models

Side by side

Hermes 4 Large 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 4 LargenousresearchThis modelGLM 4.5V ThinkingZ.aiRemove
ProvidernousresearchZ.ai
Discovery tierOpen weightsOpen weights
AddedAug 26, 2025Nov 22, 2025
Limits
Context window128KBest65.54K
Max output8.19K16.38KBest
Average output199 tokens534 tokens
Pricing, USD per 1M tokens
Input$0.30Best$0.60
Output$1.20Best$1.80
Performance
Throughput44.5 tok/s—
Time to first token0.7 s—
Request success (24h)100.0%—
Benchmark indexes
Intelligence Index7.47.6Best
Math Index15.373.0Best
Capabilities
ReasoningNoYes
VisionNoYes
Structured outputYesNo
Reasoning effort——

Public evaluations

Benchmarks

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

  • Hermes 4 Large
  • GLM 4.5V Thinking

Intelligence Index

  • Hermes 4 Large7.4
  • GLM 4.5V Thinking7.6

Hermes 4 Large: Better than 10% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Math Index

    Composite of the math evaluations

    • Hermes 4 Large: 15.3
    • GLM 4.5V Thinking: 73.0Top

Document reasoning

  • AA-LCRv1.1

    Reasoning across long documents

    • Hermes 4 Large: 22.0%Top
    • GLM 4.5V Thinking: 0.0%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Hermes 4 Large: 4.2%
    • GLM 4.5V Thinking: 6.3%Top

  • GPQA Diamond

    Graduate-level science questions

    • Hermes 4 Large: 53.6%
    • GLM 4.5V Thinking: 68.4%Top

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • Hermes 4 Large: 72.9%
    • GLM 4.5V Thinking: 78.8%Top

  • IFBench

    Following precise output instructions

    • Hermes 4 Large: 34.8%Top
    • GLM 4.5V Thinking: 34.2%

Coding

  • LiveCodeBench

    Recent competitive programming problems

    • Hermes 4 Large: 54.6%
    • GLM 4.5V Thinking: 60.4%Top

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • Hermes 4 Large: 15.3%
    • GLM 4.5V Thinking: 73.0%Top

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Hermes 4 Large: 9.8%Top
    • GLM 4.5V Thinking: 5.3%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Hermes 4 Large: 26.6%Top
    • GLM 4.5V Thinking: 22.5%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Hermes 4 Large: 22.0%Top
    • GLM 4.5V Thinking: 0.0%

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
44.5 tok/s
Faster than 34% of 263 models
Time to first token
0.7 s
Quicker than 98% of 263 models
Prompt cache hits
32.3%
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 70.5%
  • 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-4-405b",
    "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-4-405b",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

nousresearch

Other nousresearch models, starting with the same family.