NOUMENOpen app
NOUMEN

Anthropic · Frontier

Claude Sonnet 4.6

Added Feb 17, 2026

Compare models

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

Loading models…

Use in the app

Claude Sonnet 4.6 is Anthropic's most capable Sonnet yet — a full upgrade across coding, computer use, long-context reasoning, agent planning, and design. Supports up to a 1M-token context window at Sonnet pricing.

  • 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
$3.00
Output
$15.00
Cache read
$0.30

Reference prices as published by the model provider. API example

Specifications

Context window
1M
Max output
128K
Average output (7 days)
401 tokens
Longer than 40% of 473 models

Side by side

Claude Sonnet 4.6 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 4.6AnthropicThis modelInklingthinkingmachinesRemove
ProviderAnthropicthinkingmachines
Discovery tierFrontierOpen weights
AddedFeb 17, 2026Jul 15, 2026
Limits
Context window1M1.05MBest
Max output128KBest32.77K
Average output401 tokens596 tokens
Pricing, USD per 1M tokens
Input$3.00$1.00Best
Output$15.00$4.05Best
Cache read$0.30$0.17Best
Performance
Throughput78.6 tok/s—
Time to first token1.5 s—
Request success (24h)99.5%100.0%Best
Benchmark indexes
Intelligence Index24.725.0Best
Coding Index—52.1
Capabilities
ReasoningYesNo
ToolsYesYes
VisionYesYes
Structured outputYesYes
PDF inputYesNo
Audio inputNoYes
Reasoning effortlow, medium, high, xhigh, max—

Public evaluations

Benchmarks

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

  • Claude Sonnet 4.6
  • Inkling

Intelligence Index

  • Claude Sonnet 4.624.7
  • Inkling25.0

Claude Sonnet 4.6 tested at high reasoning effort

Claude Sonnet 4.6: Better than 60% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Claude Sonnet 4.6: —
    • Inkling: 52.1

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Claude Sonnet 4.6: —
    • Inkling: 5.0%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Claude Sonnet 4.6: —
    • Inkling: 0.3%

  • Harvey LAB-AAv1.1

    Legal tasks passed in full, with no material hallucination

    • Claude Sonnet 4.6: —
    • Inkling: 0.0%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Claude Sonnet 4.6: —
    • Inkling: 832 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Claude Sonnet 4.6: —
    • Inkling: 1,072 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Claude Sonnet 4.6: —
    • Inkling: 12.8%

  • AA-LCRv1.1

    Reasoning across long documents

    • Claude Sonnet 4.6: 68.3%
    • Inkling: 77.3%Top

  • MLCR-AA

    Long-context reasoning over medical records

    • Claude Sonnet 4.6: —
    • Inkling: 6.1%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Claude Sonnet 4.6: 13.3%
    • Inkling: 31.9%Top

  • GPQA Diamond

    Graduate-level science questions

    • Claude Sonnet 4.6: 79.9%
    • Inkling: 87.2%Top

  • IFBench

    Following precise output instructions

    • Claude Sonnet 4.6: 41.2%
    • Inkling: —

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Claude Sonnet 4.6: —
    • Inkling: 1.0%

  • SciCode

    Scientific computing in Python

    • Claude Sonnet 4.6: —
    • Inkling: 47.0%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Claude Sonnet 4.6: 46.2%
    • Inkling: —

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Claude Sonnet 4.6: 79.5%
    • Inkling: —

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Claude Sonnet 4.6: 68.3%
    • Inkling: 77.3%Top

Scores from Artificial Analysis, updated Oct 26, 2026. Claude Sonnet 4.6 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
78.6 tok/s
Faster than 52% of 256 models
Time to first token
1.5 s
Quicker than 85% of 256 models
Prompt cache hits
37.1%
About $2.00 per 1M input tokens with caching
Request success (24h)
99.5%
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 65.8%
  • 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-4.6",
    "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-4.6",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Anthropic

Other Anthropic models, starting with the same family.