NOUMENOpen app
NOUMEN

celeris · Balanced

Celeris 1

Added Jul 25, 2026

Compare models

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

Loading models…

Use in the app

Celeris 1 is a diffusion language model built for ultra-low-latency classification, extraction, judging, query rewriting, and other short structured responses.

Input
Text
Output
Text
Discovery tier
Balanced

Pricing

USD per 1M tokens
Input
$2.00
Output
$6.00

Reference prices as published by the model provider. API example

Specifications

Context window
8.2K
Max output
8.2K

Side by side

Celeris 1 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…

Celeris 1celerisThis modelLlama 4 ScoutMetaRemove
ProvidercelerisMeta
Discovery tierBalancedOpen weights
AddedJul 25, 2026Sep 5, 2025
Limits
Context window8.19K328KBest
Max output8.19K65.54KBest
Average output—79 tokens
Pricing, USD per 1M tokens
Input$2.00$0.085Best
Output$6.00$0.46Best
Performance
Request success (24h)—60.0%
Benchmark indexes
Intelligence Index6.36.5Best
Coding Index14.4Best8.2
Math Index—14.0
Capabilities
ToolsNoYes
VisionNoYes
Structured outputNoYes
Reasoning effort——

Public evaluations

Benchmarks

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

  • Celeris 1
  • Llama 4 Scout

Intelligence Index

  • Celeris 16.3
  • Llama 4 Scout6.5

Celeris 1: Better than 4% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Celeris 1: 14.4Top
    • Llama 4 Scout: 8.2

  • Math Index

    Composite of the math evaluations

    • Celeris 1: —
    • Llama 4 Scout: 14.0

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Celeris 1: 0.4%Top
    • Llama 4 Scout: 0.2%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Celeris 1: 0.2%Top
    • Llama 4 Scout: 0.0%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Celeris 1: 151 Elo
    • Llama 4 Scout: —

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Celeris 1: 301 Elo
    • Llama 4 Scout: —

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Celeris 1: 1.2%Top
    • Llama 4 Scout: 0.0%

  • AA-LCRv1.1

    Reasoning across long documents

    • Celeris 1: 38.0%Top
    • Llama 4 Scout: 27.7%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Celeris 1: 6.8%Top
    • Llama 4 Scout: 3.8%

  • GPQA Diamond

    Graduate-level science questions

    • Celeris 1: 63.1%Top
    • Llama 4 Scout: 58.7%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • Celeris 1: 78.0%Top
    • Llama 4 Scout: 75.2%

  • IFBench

    Following precise output instructions

    • Celeris 1: —
    • Llama 4 Scout: 39.5%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Celeris 1: 0.0%Top
    • Llama 4 Scout: 0.0%Top

  • SciCode

    Scientific computing in Python

    • Celeris 1: 21.6%Top
    • Llama 4 Scout: 21.3%

  • LiveCodeBench

    Recent competitive programming problems

    • Celeris 1: —
    • Llama 4 Scout: 29.9%

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • Celeris 1: —
    • Llama 4 Scout: 14.0%

  • AIME

    Competition mathematics

    • Celeris 1: —
    • Llama 4 Scout: 28.3%

  • MATH-500

    Competition math problems

    • Celeris 1: —
    • Llama 4 Scout: 84.4%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Celeris 1: —
    • Llama 4 Scout: 1.5%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Celeris 1: —
    • Llama 4 Scout: 15.5%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Celeris 1: 38.0%Top
    • Llama 4 Scout: 27.7%

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

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": "celeris-1",
    "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="celeris-1",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)