Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models828Deals30d255Policy30d74, 17 pendingSources1,167

Claude Opus 5.5

AnthropicReleased Sep 22, 2026Current

Score basis

Claude Opus 5.5 is at the frontier in math; strong in factuality, reasoning, long context, and coding; and capable in agentic tasks and multimodal tasks. 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.

Frontier1 capability
  1. Math−3.2%5 of 5
Strong4 capabilities
  1. Factuality−4.3%4 of 4
  2. Reasoning−5.2%5 of 6
  3. Long Context−7.0%1 of 3
  4. Coding−8.7%6 of 10
Capable2 capabilities
  1. Agentic−13.0%5 of 7
  2. Multimodal−21.4%1 of 6
Not rated3 capabilities

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

Price

$4.00input$20.00outputper million tokens

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

Costs more than 91% of 327 priced models · 3:1 input-to-output blend, log scale

Evidence

166results on98benchmarks

  • 36 independently verified
  • 58 aggregator
  • 34 vendor-reported
  • 38 cross-referenced

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

API features

Tool callingStructured outputsReasoning

As listed by OpenRouter

Research

52 papers reference Claude Opus 5.5

Claude Opus 5.5 benchmark results

166 results on 98 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.

Math

FrontierFull math ranking

3.2% behind the leader5 of 5 ranked benchmarks measured

Show 1 more math resultHide 1 math result

Factuality

StrongFull factuality ranking

4.3% behind the leader4 of 4 ranked benchmarks measured

Show 8 more factuality resultsHide 8 factuality results

Reasoning

StrongFull reasoning ranking

5.2% behind the leader5 of 6 ranked benchmarks measured

Show 13 more reasoning resultsHide 13 reasoning results

Long Context

StrongFull long context ranking

7.0% behind the leader1 of 3 ranked benchmarks measured

Show 3 more long context resultsHide 3 long context results

Coding

StrongFull coding ranking

8.7% behind the leader6 of 10 ranked benchmarks measured

Show 5 more coding resultsHide 5 coding results

Agentic

CapableFull agentic ranking

13.0% behind the leader5 of 7 ranked benchmarks measured

Show 8 more agentic resultsHide 8 agentic results

Multimodal

CapableFull multimodal ranking

21.4% behind the leader1 of 6 ranked benchmarks measured

Show 5 more multimodal resultsHide 5 multimodal results

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 91 more resultsHide 91 results

Claude Opus 5.5: common questions

Who makes Claude Opus 5.5?

Claude Opus 5.5 is made by Anthropic.

When was Claude Opus 5.5 released?

Claude Opus 5.5 was released on Sep 22, 2026, according to Anthropic's own announcement.

What is Claude Opus 5.5 good at?

Claude Opus 5.5 is at the frontier in math; strong in factuality, reasoning, long context, and coding; and capable in agentic tasks and multimodal tasks. Too few results yet to rate safety, multilingual tasks, or instruction following.

How much does Claude Opus 5.5 cost?

Claude Opus 5.5 costs $4.00 per million input tokens and $20.00 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 91% of the 327 priced models we track.

How many benchmarks has Claude Opus 5.5 been tested on?

We track 166 results for Claude Opus 5.5 on 98 benchmarks from 25 sources, 36 of them independently verified. The latest was recorded on Nov 8, 2026.

Which API features does Claude Opus 5.5 support?

OpenRouter lists tool calling, structured outputs, and reasoning for Claude Opus 5.5.

About this record

Where Claude Opus 5.5's numbers come from, and every name it appears under.

Tracked since
Sep 22, 2026
Newest source mention
Nov 9, 2026

Where the results come from

Verification: 166 scores · 36 independently verified · 58 aggregator-attributed · 38 vendor cross-reference · 34 vendor-reported. How these tiers are assigned

From 25 sources on 14 sites. Artificial Analysis supplies 60 of them; the 36 independently verified results come from 9 sites. Bars are coloured by trust tier.

  • artificialanalysis.ai60
  • deepmind.google23
  • api.llm-stats.com17
  • huggingface.co15
  • livebench.ai13
  • www-cdn.anthropic.com11
  • arcprize.org8
  • anthropic.com6
  • raw.githubusercontent.com4
  • epoch.ai3
  • datasets-server.huggingface.co2
  • labs.scale.com2
  • lmarena.ai1
  • simple-bench.com1

Also known as

How our sources name Claude Opus 5.5 at each reasoning setting.

SettingShort formLong formAPI id
lowclaude opus 5.5 (low)Claude Opus 5.5 (Adaptive Reasoning, Low Effort, Default Fallback)claude-opus-5-5-low
mediumclaude opus 5.5 (medium)claude opus 5.5 (adaptive reasoning, medium effort, default fallback)claude-opus-5-5-medium
highclaude opus 5.5 (high)Claude Opus 5.5 (Adaptive Reasoning, High Effort, Default Fallback)claude-opus-5-5-high claude-opus-5.5-high
xhighclaude opus 5.5 (xhigh) opus-5.5 xhigh—claude-opus-5-5-xhigh
maxclaude opus 5.5 (max)Claude Opus 5.5 (Adaptive Reasoning, Max Effort, Default Fallback)claude-opus-5.5-max claude-opus-5-5-max
Also listed asclaude 5.5 opusclaude-opus-5-5opus 5.5opus5.5what's new in claude opus 5.5opus 55claude (opus 5.5)