Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d271Policy30d66, 14 pendingSources1,015

Claude Sonnet 5

AnthropicReleased Jun 30, 2026Current

Score basis

Claude Sonnet 5 is strong in long context; capable in agentic tasks, coding, reasoning, multimodal tasks, and factuality; and behind the leaders in math. Too few results yet to rate safety, multilingual tasks, or instruction following.

Capability profile

Bars show the model's median result as a share of the leading model's, per capability. Select a row to see its results.

Strong1 capability
  1. Long Context−5.6%2 of 3
Capable5 capabilities
  1. Agentic−13.8%6 of 7
  2. Coding−14.3%8 of 10
  3. Reasoning−15.5%5 of 6
  4. Multimodal−20.6%2 of 6
  5. Factuality−23.8%3 of 4
Limited1 capability
  1. Math−33.2%3 of 5
Not rated3 capabilities

Too few results yet to rate Safety, Multilingual or Instruction Following.

Price

$2.00input$10.00outputper million tokens

From Anthropic's own price page · 4 providers tracked · All prices

Costs more than 82% of 330 priced models · 3:1 input-to-output blend, log scale

Evidence

153results on81benchmarks

  • 20 independently verified
  • 69 aggregator
  • 50 vendor-reported
  • 14 cross-referenced

From 23 sources · latest Oct 8, 2026 · How verification works

API features

Tool callingStructured outputsReasoning

As listed by OpenRouter

Research

27 papers reference Claude Sonnet 5

Claude Sonnet 5 benchmark results

153 results on 81 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.

Long Context

StrongFull long context ranking

5.6% behind the leader2 of 3 ranked benchmarks measured

Show 4 more long context resultsHide 4 long context results

Agentic

CapableFull agentic ranking

13.8% behind the leader6 of 7 ranked benchmarks measured

Show 10 more agentic resultsHide 10 agentic results

Coding

CapableFull coding ranking

14.3% behind the leader8 of 10 ranked benchmarks measured

Show 8 more coding resultsHide 8 coding results

Reasoning

CapableFull reasoning ranking

15.5% behind the leader5 of 6 ranked benchmarks measured

Show 13 more reasoning resultsHide 13 reasoning results

Multimodal

CapableFull multimodal ranking

20.6% behind the leader2 of 6 ranked benchmarks measured

Show 4 more multimodal resultsHide 4 multimodal results

Factuality

CapableFull factuality ranking

23.8% behind the leader3 of 4 ranked benchmarks measured

Show 11 more factuality resultsHide 11 factuality results

Math

LimitedFull math ranking

33.2% behind the leader3 of 5 ranked benchmarks measured

Show 1 more math resultHide 1 math result

Instruction Following

Not enough dataFull instruction following ranking

0 of 3 ranked benchmarks measured

More results

Benchmarks outside the capability baskets. They are not ranked against a leader.

Show 67 more resultsHide 67 results

Claude Sonnet 5: common questions

Who makes Claude Sonnet 5?

Claude Sonnet 5 is made by Anthropic.

When was Claude Sonnet 5 released?

Claude Sonnet 5 was released on Jun 30, 2026, according to Artificial Analysis.

What is Claude Sonnet 5 good at?

Claude Sonnet 5 is strong in long context; capable in agentic tasks, coding, reasoning, multimodal tasks, and factuality; and behind the leaders in math. Too few results yet to rate safety, multilingual tasks, or instruction following.

How much does Claude Sonnet 5 cost?

Claude Sonnet 5 costs $2.00 per million input tokens and $10.00 per million output tokens, according to Anthropic's own price page. We track its price at 4 providers. At a mix of three input tokens to one output token, it costs more than 82% of the 330 priced models we track.

How many benchmarks has Claude Sonnet 5 been tested on?

We track 153 results for Claude Sonnet 5 on 81 benchmarks from 23 sources, 20 of them independently verified. The latest was recorded on Oct 8, 2026.

Which API features does Claude Sonnet 5 support?

OpenRouter lists tool calling, structured outputs, and reasoning for Claude Sonnet 5.

About this record

Where Claude Sonnet 5's numbers come from, and every name it appears under.

Tracked since
Jul 1, 2026
Newest source mention
Sep 10, 2026

Where the results come from

Verification: 153 scores · 20 independently verified · 69 aggregator-attributed · 14 vendor cross-reference · 50 vendor-reported. How these tiers are assigned

From 23 sources on 10 sites. Artificial Analysis supplies 73 of them; the 20 independently verified results come from 6 sites. Bars are coloured by trust tier.

  • artificialanalysis.ai73
  • www-cdn.anthropic.com33
  • api.llm-stats.com16
  • deepmind.google14
  • livebench.ai7
  • epoch.ai4
  • datasets-server.huggingface.co3
  • anthropic.com1
  • lmarena.ai1
  • simple-bench.com1

Also known as

How our sources name Claude Sonnet 5 at each reasoning setting.

SettingShort formLong formAPI id
lowclaude sonnet 5 (low)claude sonnet 5 (adaptive reasoning, low effort)claude-sonnet-5-low
mediumclaude sonnet 5 (medium)claude sonnet 5 (adaptive reasoning, medium effort)claude-sonnet-5-medium
highclaude sonnet 5 (high)claude sonnet 5 (adaptive reasoning, high effort) claude sonnet 5 (non-reasoning, high effort)claude-sonnet-5-high
xhighclaude sonnet 5 (xhigh)claude sonnet 5 (adaptive reasoning, xhigh effort)claude-sonnet-5-xhigh
maxclaude sonnet 5 (max)claude sonnet 5 (adaptive reasoning, max effort)—
Also listed asclaude-sonnet-5-non-reasoningclaude-sonnet-5-thinkingclaude-sonnet-5:batchsonnet 5claude 5 sonnetclaude sonnet 5 (non-reasoning)