NOUMENOpen app
NOUMEN

Anthropic · Frontier

Claude Opus 5.5

Added Sep 22, 2026

Compare models

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

Loading models…

Use in the app

Claude Opus 5.5 is Anthropic's flagship model for agentic coding, computer use, complex knowledge work, and long-running tasks, with improved efficiency and more natural communication.

  • Reasoning
  • Tools
  • Vision
  • Structured output
  • PDF input
Input
Text, Images
Output
Text
Reasoning effort
low · medium · high · xhigh · max
Discovery tier
Frontier

Pricing

USD per 1M tokens
Input
$4.00
Output
$20.00
Cache read
$0.20
Cache write
$5.00
$8.00 for a 1-hour cache

Reference prices as published by the model provider. API example

Specifications

Context window
1M
Max output
128K
Average output (7 days)
2K tokens
Longer than 92% of 473 models

Side by side

Claude Opus 5.5 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…

Claude Opus 5.5AnthropicThis modelMuse WonderMetaRemove
ProviderAnthropicMeta
Discovery tierFrontierFrontier
AddedSep 22, 2026Oct 12, 2026
Limits
Context window1M1.05MBest
Max output128K—
Average output2K tokens1.2K tokens
Pricing, USD per 1M tokens
Input$4.00$4.00
Output$20.00$20.00
Cache read$0.20$0.20
Cache write$5.00—
Performance
Throughput116.0 tok/sBest102.6 tok/s
Time to first token6.5 s1.8 sBest
Request success (24h)99.8%Best99.5%
Benchmark indexes
Intelligence Index53.6Best52.4
Capabilities
ReasoningYesYes
ToolsYesYes
VisionYesYes
Structured outputYesYes
PDF inputYesYes
Audio inputNoYes
Video inputNoYes
Reasoning effortlow, medium, high, xhigh, maxminimal, low, medium, high, xhigh, max

Public evaluations

Benchmarks

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

  • Claude Opus 5.5
  • Muse Wonder

Intelligence Index

  • Claude Opus 5.553.6
  • Muse Wonder52.4

Claude Opus 5.5 tested at high reasoning effort

Claude Opus 5.5: Better than 98% of 326 scored models

3.8Catalog models by score55.1

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Claude Opus 5.5: 63.2%
    • Muse Wonder: 68.1%Top

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Claude Opus 5.5: 33.8%
    • Muse Wonder: 39.1%Top

  • Harvey LAB-AAv1.1

    Legal tasks passed in full, with no material hallucination

    • Claude Opus 5.5: —
    • Muse Wonder: 10.0%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Claude Opus 5.5: 1,683 EloTop
    • Muse Wonder: 1,659 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Claude Opus 5.5: 1,704 Elo
    • Muse Wonder: 1,770 EloTop

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Claude Opus 5.5: 28.8%
    • Muse Wonder: 30.6%Top

  • AA-LCRv1.1

    Reasoning across long documents

    • Claude Opus 5.5: 82.7%Top
    • Muse Wonder: 80.7%

  • MLCR-AA

    Long-context reasoning over medical records

    • Claude Opus 5.5: 15.0%
    • Muse Wonder: 22.2%Top

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Claude Opus 5.5: 55.6%Top
    • Muse Wonder: 50.1%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Claude Opus 5.5: 56.6%Top
    • Muse Wonder: 52.0%

  • SciCode

    Scientific computing in Python

    • Claude Opus 5.5: 60.4%Top
    • Muse Wonder: 60.3%

Legacy evaluations

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Claude Opus 5.5: 82.7%Top
    • Muse Wonder: 80.7%

Scores from Artificial Analysis, updated Oct 26, 2026. Claude Opus 5.5 was tested at high reasoning effort; compare scores measured at the same effort.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
116.0 tok/s
Faster than 67% of 260 models
Time to first token
6.5 s
Quicker than 21% of 260 models
Prompt cache hits
76.7%
About $1.09 per 1M input tokens with caching
Request success (24h)
99.8%
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 79.5%
  • 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": "anthropic/claude-opus-5.5",
    "reasoning_effort": "medium",
    "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="anthropic/claude-opus-5.5",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Anthropic

Other Anthropic models, starting with the same family.