nousresearch · Open weights
Hermes 4 Large
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
Compare models
Put Hermes 4 Large next to up to three other models. The comparison stays in the link, so you can share it.
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
Intelligence Index
7.4
Better than 10% of 326 scored models
Indexes
Math Index
15.3Composite of the math evaluations
Better than 16% of 118 scored models
Document reasoning
AA-LCRv1.1
22.0%Reasoning across long documents
Better than 10% of 309 scored models
Reasoning and knowledge
Humanity’s Last Exam
4.2%Expert-level questions across academic fields
Better than 8% of 323 scored models
GPQA Diamond
53.6%Graduate-level science questions
Better than 12% of 291 scored models
MMLU-Pro
72.9%Multi-subject knowledge and reasoning
Better than 28% of 132 scored models
IFBench
34.8%Following precise output instructions
Better than 15% of 215 scored models
Coding
LiveCodeBench
54.6%Recent competitive programming problems
Better than 46% of 129 scored models
Math
AIME 2025
15.3%Competition mathematics, 2025 problems
Better than 16% of 118 scored models
Legacy evaluations
Terminal-Bench Hard
9.8%Earlier terminal task suite
Better than 21% of 212 scored models
τ²-Bench Telecom
26.6%Tool use in a customer-support simulation
Better than 16% of 214 scored models
AA-LCR (unversioned)
22.0%Long-context reasoning, earlier grading
Better than 10% of 309 scored models
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 32% of 261 models
- Time to first token
- 0.5 s
- Quicker than 99% of 261 models
- Prompt cache hits
- 13.7%
- 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.
- 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.
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
Related models
Other nousresearch models, starting with the same family.