Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d271Policy30d67, 15 pendingSources1,014

Claude 3.7 Sonnet

AnthropicReleased Feb 24, 2025Current

Score basis

Claude 3.7 Sonnet is capable in factuality; and behind the leaders in multimodal tasks, coding, long context, agentic tasks, and instruction following. Too few results yet to rate reasoning, safety, math, or multilingual tasks.

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.

Capable1 capability
  1. Factuality−22.4%2 of 4
Limited5 capabilities
  1. Multimodal−34.9%2 of 6
  2. Coding−35.0%3 of 10
  3. Long Context−36.2%1 of 3
  4. Agentic−37.9%1 of 7
  5. Instruction Following−41.6%2 of 3
Not rated4 capabilities

Too few results yet to rate Reasoning, Safety, Math or Multilingual.

Price

$3.00input$15.00outputper million tokens

From Artificial Analysis · All prices

Costs more than 88% of 330 priced models · 3:1 input-to-output blend, log scale

Evidence

81results on50benchmarks

  • 36 independently verified
  • 30 aggregator
  • 15 vendor-reported

From 25 sources · latest Oct 8, 2026 · How verification works

Research

5 papers reference Claude 3.7 Sonnet

Claude 3.7 Sonnet benchmark results

81 results on 50 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.

Factuality

CapableFull factuality ranking

22.4% behind the leader2 of 4 ranked benchmarks measured

Show 2 more factuality resultsHide 2 factuality results

Multimodal

LimitedFull multimodal ranking

34.9% behind the leader2 of 6 ranked benchmarks measured

Show 4 more multimodal resultsHide 4 multimodal results

Coding

LimitedFull coding ranking

35.0% behind the leader3 of 10 ranked benchmarks measured

Show 4 more coding resultsHide 4 coding results

Long Context

LimitedFull long context ranking

36.2% behind the leader1 of 3 ranked benchmarks measured

Show 1 more long context resultHide 1 long context result

Agentic

LimitedFull agentic ranking

37.9% behind the leader1 of 7 ranked benchmarks measured

Show 1 more agentic resultHide 1 agentic result

Instruction Following

LimitedFull instruction following ranking

41.6% behind the leader2 of 3 ranked benchmarks measured

Show 2 more instruction following resultsHide 2 instruction following results

Reasoning

Not enough dataFull reasoning ranking

0 of 6 ranked benchmarks measured

Show 10 more reasoning resultsHide 10 reasoning results

More results

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

Show 37 more resultsHide 37 results

Claude 3.7 Sonnet: common questions

Who makes Claude 3.7 Sonnet?

Claude 3.7 Sonnet is made by Anthropic.

When was Claude 3.7 Sonnet released?

Claude 3.7 Sonnet was released on Feb 24, 2025, according to Artificial Analysis.

What is Claude 3.7 Sonnet good at?

Claude 3.7 Sonnet is capable in factuality; and behind the leaders in multimodal tasks, coding, long context, agentic tasks, and instruction following. Too few results yet to rate reasoning, safety, math, or multilingual tasks.

How much does Claude 3.7 Sonnet cost?

Claude 3.7 Sonnet costs $3.00 per million input tokens and $15.00 per million output tokens, according to Artificial Analysis. At a mix of three input tokens to one output token, it costs more than 88% of the 330 priced models we track.

How many benchmarks has Claude 3.7 Sonnet been tested on?

We track 81 results for Claude 3.7 Sonnet on 50 benchmarks from 25 sources, 36 of them independently verified. The latest was recorded on Oct 8, 2026.

About this record

Where Claude 3.7 Sonnet's numbers come from, and every name it appears under.

Tracked since
Jun 18, 2026
Newest source mention
Sep 1, 2026

Where the results come from

Verification: 81 scores · 36 independently verified · 30 aggregator-attributed · 15 vendor-reported. How these tiers are assigned

From 25 sources on 15 sites. Artificial Analysis supplies 31 of them; the 36 independently verified results come from 12 sites. Bars are coloured by trust tier.

  • artificialanalysis.ai31
  • api.llm-stats.com10
  • arcprize.org8
  • storage.googleapis.com6
  • matharena.ai4
  • www-cdn.anthropic.com4
  • huggingface.co3
  • raw.githubusercontent.com3
  • aider.chat2
  • datasets-server.huggingface.co2
  • lmarena.ai2
  • simple-bench.com2
  • swebench.com2
  • anthropic.com1
  • labs.scale.com1

Also known as

claude 3.7claude 3.7 sonnet (20250219)claude 3.7 sonnet (february 2025)claude 3.7 sonnet (inspect)claude 3.7 sonnet (non-reasoning)claude 3.7 sonnet (reasoning)claude 3.7 sonnet (thinking)claude 3.7 sonnet (thinking) (february 2025)Claude 3.7 Sonnet 20250219 (32k thinking tokens)claude 3.7 sonnet thinking (feb 2025)claude sonnet 3.7claude-3-7-sonnetclaude-3-7-sonnet-20250219claude-3-7-sonnet-20250219 (32k thinking tokens)claude-3-7-sonnet-20250219 (no thinking)claude-3-7-sonnet-20250219-thinking-25kand 10 more