NOUMENOpen app
NOUMEN

Anthropic · Frontier

Claude Sonnet 5.5

Added Sep 28, 2026

Compare models

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

Loading models…

Use in the app

Claude Sonnet 5.5 handles everyday coding, tool-based workflows, visual analysis, and polished writing with a 1M-token context window. This version skips up-front thinking and can reason between tool calls for faster responses; use Thinking for deeper planning and complex problems.

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

Pricing

USD per 1M tokens
Input
$2.00
Output
$10.00
Cache read
$0.10
Cache write
$2.50
$4.00 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)
523 tokens
Longer than 50% of 473 models

Side by side

Claude Sonnet 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 Sonnet 5.5AnthropicThis modelClaude Sonnet LatestAnthropicRemove
ProviderAnthropicAnthropic
Discovery tierFrontierFrontier
AddedSep 28, 2026Mar 1, 2026
Limits
Context window1M1M
Max output128K128K
Average output523 tokens1K tokens
Pricing, USD per 1M tokens
Input$2.00$2.00
Output$10.00$10.00
Cache read$0.10$0.10
Cache write$2.50$2.50
Performance
Throughput152.3 tok/s238.5 tok/sBest
Time to first token4.8 sBest5.4 s
Request success (24h)99.8%Best99.1%
Benchmark indexes
Intelligence Index46.846.8
Capabilities
ReasoningYesYes
ToolsYesYes
VisionYesYes
Structured outputYesYes
PDF inputYesYes
Reasoning effortlow, medium, highlow, medium, high, xhigh, max

Public evaluations

Benchmarks

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

  • Claude Sonnet 5.5
  • Claude Sonnet Latest

Intelligence Index

  • Claude Sonnet 5.546.8
  • Claude Sonnet Latest46.8

Claude Sonnet 5.5 tested at high reasoning effort

Claude Sonnet 5.5: Better than 93% of 326 scored models

3.8Catalog models by score55.1

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Claude Sonnet 5.5: 59.4%Top
    • Claude Sonnet Latest: 59.4%Top

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Claude Sonnet 5.5: 29.4%Top
    • Claude Sonnet Latest: 29.4%Top

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Claude Sonnet 5.5: 1,635 EloTop
    • Claude Sonnet Latest: 1,635 EloTop

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Claude Sonnet 5.5: 1,548 EloTop
    • Claude Sonnet Latest: 1,548 EloTop

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Claude Sonnet 5.5: 25.2%Top
    • Claude Sonnet Latest: 25.2%Top

  • AA-LCRv1.1

    Reasoning across long documents

    • Claude Sonnet 5.5: 78.0%Top
    • Claude Sonnet Latest: 78.0%Top

  • MLCR-AA

    Long-context reasoning over medical records

    • Claude Sonnet 5.5: 18.9%Top
    • Claude Sonnet Latest: 18.9%Top

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Claude Sonnet 5.5: 45.8%Top
    • Claude Sonnet Latest: 45.8%Top

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Claude Sonnet 5.5: 43.9%Top
    • Claude Sonnet Latest: 43.9%Top

  • SciCode

    Scientific computing in Python

    • Claude Sonnet 5.5: 53.7%Top
    • Claude Sonnet Latest: 53.7%Top

Legacy evaluations

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Claude Sonnet 5.5: 78.0%Top
    • Claude Sonnet Latest: 78.0%Top

Scores from Artificial Analysis, updated Oct 26, 2026. Claude Sonnet 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
152.3 tok/s
Faster than 77% of 260 models
Time to first token
4.8 s
Quicker than 33% of 260 models
Prompt cache hits
42.9%
About $1.19 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 93.9%
  • 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-sonnet-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-sonnet-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.