NOUMENOpen app
NOUMEN

Anthropic · Frontier

Claude Sonnet Latest

Added Mar 1, 2026

Compare models

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

Loading models…

Use in the app

Compatibility alias that routes to the newest version of Claude Sonnet. Currently routes to Claude Sonnet 5.5 Thinking.

  • 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
$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)
1K tokens
Longer than 71% of 473 models

Side by side

Claude Sonnet Latest 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 LatestAnthropicThis modelMiMo V2.6 ProxiaomiRemove
ProviderAnthropicxiaomi
Discovery tierFrontierOpen weights
AddedMar 1, 2026Sep 21, 2026
Limits
Context window1M1.05MBest
Max output128K131.07KBest
Average output1K tokens1.2K tokens
Pricing, USD per 1M tokens
Input$2.00$0.44Best
Output$10.00$0.87Best
Cache read$0.10$0.0036Best
Cache write$2.50$0.00Best
Performance
Throughput237.9 tok/sBest34.8 tok/s
Time to first token5.4 s3.7 sBest
Request success (24h)99.1%99.8%Best
Benchmark indexes
Intelligence Index46.8Best46.3
Capabilities
ReasoningYesYes
ToolsYesYes
VisionYesYes
Structured outputYesYes
PDF inputYesNo
Audio inputNoYes
Video inputNoYes
Reasoning effortlow, medium, high, xhigh, maxnone, high

Public evaluations

Benchmarks

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

  • Claude Sonnet Latest
  • MiMo V2.6 Pro

Intelligence Index

  • Claude Sonnet Latest46.8
  • MiMo V2.6 Pro46.3

Claude Sonnet Latest tested at high reasoning effort

Claude Sonnet Latest: 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 Latest: 59.4%Top
    • MiMo V2.6 Pro: 58.6%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Claude Sonnet Latest: 29.4%Top
    • MiMo V2.6 Pro: 25.4%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Claude Sonnet Latest: 1,635 EloTop
    • MiMo V2.6 Pro: 1,512 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Claude Sonnet Latest: 1,548 Elo
    • MiMo V2.6 Pro: 1,683 EloTop

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Claude Sonnet Latest: 25.2%Top
    • MiMo V2.6 Pro: 19.2%

  • AA-LCRv1.1

    Reasoning across long documents

    • Claude Sonnet Latest: 78.0%
    • MiMo V2.6 Pro: 86.3%Top

  • MLCR-AA

    Long-context reasoning over medical records

    • Claude Sonnet Latest: 18.9%Top
    • MiMo V2.6 Pro: 12.8%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Claude Sonnet Latest: 45.8%
    • MiMo V2.6 Pro: 49.4%Top

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Claude Sonnet Latest: 43.9%Top
    • MiMo V2.6 Pro: 34.8%

  • SciCode

    Scientific computing in Python

    • Claude Sonnet Latest: 53.7%
    • MiMo V2.6 Pro: 60.9%Top

Legacy evaluations

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Claude Sonnet Latest: 78.0%
    • MiMo V2.6 Pro: 86.3%Top

Scores from Artificial Analysis, updated Oct 26, 2026. Claude Sonnet Latest 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
237.9 tok/s
Faster than 89% of 256 models
Time to first token
5.4 s
Quicker than 26% of 256 models
Prompt cache hits
0.0%
About $2.00 per 1M input tokens with caching
Request success (24h)
99.1%
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 96.9%
  • 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-latest",
    "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-latest",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Anthropic

Other Anthropic models, starting with the same family.