Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models739Deals30d257Policy30d64, 14 pendingSources1,010

Claude Opus 4.5

AnthropicReleased Nov 24, 2025Current

Score basis

Claude Opus 4.5 is strong in long context; capable in factuality and multimodal tasks; and behind the leaders in reasoning, coding, agentic tasks, instruction following, and math. Too few results yet to rate safety 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.

Strong1 capability
  1. Long Context−8.5%2 of 3
Capable2 capabilities
  1. Factuality−22.3%4 of 4
  2. Multimodal−22.7%5 of 6
Limited5 capabilities
  1. Reasoning−27.6%5 of 6
  2. Coding−31.4%9 of 10
  3. Agentic−39.2%4 of 7
  4. Instruction Following−40.1%3 of 3
  5. Math−51.0%3 of 5
Not rated2 capabilities

Too few results yet to rate Safety or Multilingual.

Price

$5.00input$25.00outputper million tokens

From Anthropic's own price page · 3 providers tracked · All prices

Costs more than 93% of 331 priced models · 3:1 input-to-output blend, log scale

Evidence

205results on128benchmarks

  • 44 independently verified
  • 32 aggregator
  • 31 vendor-reported
  • 98 cross-referenced

From 26 sources · latest Oct 8, 2026 · How verification works

API features

Tool callingStructured outputsReasoning

As listed by OpenRouter

Research

13 papers reference Claude Opus 4.5

Claude Opus 4.5 benchmark results

205 results on 128 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

8.5% behind the leader2 of 3 ranked benchmarks measured

Show 1 more long context resultHide 1 long context result

Factuality

CapableFull factuality ranking

22.3% behind the leader4 of 4 ranked benchmarks measured

Show 2 more factuality resultsHide 2 factuality results

Multimodal

CapableFull multimodal ranking

22.7% behind the leader5 of 6 ranked benchmarks measured

Show 6 more multimodal resultsHide 6 multimodal results

Reasoning

LimitedFull reasoning ranking

27.6% behind the leader5 of 6 ranked benchmarks measured

Show 15 more reasoning resultsHide 15 reasoning results

Coding

LimitedFull coding ranking

31.4% behind the leader9 of 10 ranked benchmarks measured

Show 19 more coding resultsHide 19 coding results

Agentic

LimitedFull agentic ranking

39.2% behind the leader4 of 7 ranked benchmarks measured

Show 4 more agentic resultsHide 4 agentic results

Instruction Following

LimitedFull instruction following ranking

40.1% behind the leader3 of 3 ranked benchmarks measured

Show 2 more instruction following resultsHide 2 instruction following results

Math

LimitedFull math ranking

51.0% behind the leader3 of 5 ranked benchmarks measured

Show 4 more math resultsHide 4 math results

More results

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

Show 111 more resultsHide 111 results

Claude Opus 4.5: common questions

Who makes Claude Opus 4.5?

Claude Opus 4.5 is made by Anthropic.

When was Claude Opus 4.5 released?

Claude Opus 4.5 was released on Nov 24, 2025, according to Artificial Analysis.

What is Claude Opus 4.5 good at?

Claude Opus 4.5 is strong in long context; capable in factuality and multimodal tasks; and behind the leaders in reasoning, coding, agentic tasks, instruction following, and math. Too few results yet to rate safety or multilingual tasks.

How much does Claude Opus 4.5 cost?

Claude Opus 4.5 costs $5.00 per million input tokens and $25.00 per million output tokens, according to Anthropic's own price page. We track its price at 3 providers. At a mix of three input tokens to one output token, it costs more than 93% of the 331 priced models we track.

How many benchmarks has Claude Opus 4.5 been tested on?

We track 205 results for Claude Opus 4.5 on 128 benchmarks from 26 sources, 44 of them independently verified. The latest was recorded on Oct 8, 2026.

Which API features does Claude Opus 4.5 support?

OpenRouter lists tool calling, structured outputs, and reasoning for Claude Opus 4.5.

About this record

Where Claude Opus 4.5's numbers come from, and every name it appears under.

Tracked since
Apr 27, 2026
Newest source mention
Sep 7, 2026

Where the results come from

Verification: 205 scores · 44 independently verified · 32 aggregator-attributed · 98 vendor cross-reference · 31 vendor-reported. How these tiers are assigned

From 26 sources on 14 sites. Hugging Face supplies 98 of them; the 44 independently verified results come from 10 sites. Bars are coloured by trust tier.

  • huggingface.co98
  • artificialanalysis.ai33
  • www-cdn.anthropic.com19
  • arcprize.org12
  • api.llm-stats.com9
  • livebench.ai7
  • raw.githubusercontent.com7
  • swebench.com5
  • epoch.ai4
  • anthropic.com3
  • labs.scale.com3
  • datasets-server.huggingface.co2
  • lmarena.ai2
  • simple-bench.com1

Also known as

How our sources name Claude Opus 4.5 at each reasoning setting.

SettingShort formAPI id
mediumclaude 4.5 opus medium (20251101) claude 4.5 opus (20251101) (medium)—
highclaude 4.5 opus (high reasoning) Claude 4.5 Opus (high)claude-opus-4-5 (high)
Also listed asclaude 4.5 opusClaude Opus 4-5-20251101 Thinkingclaude opus 4.5 (16k thinking)claude opus 4.5 (32k thinking)claude opus 4.5 (inspect)claude opus 4.5 (no thinking)claude opus 4.5 (non-reasoning)claude opus 4.5 (reasoning)claude opus 4.5 thinkingClaude Opus 4.5:batchclaude-opus-4-5claude-opus-4-5-20251101claude-opus-4-5-20251101-thinking-32kclaude-opus-4-5-thinkingopus 4.5opus 4.5 (thinking, 16k)and 6 more