Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d270Policy30d65, 13 pendingSources1,015

Claude Opus 4

AnthropicReleased May 22, 2025Current

Score basis

Claude Opus 4 is behind the leaders in long context, coding, instruction following, and reasoning. Too few results yet to rate agentic tasks, safety, math, multimodal tasks, multilingual tasks, or factuality.

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.

Limited4 capabilities
  1. Long Context−27.4%2 of 3
  2. Coding−34.0%4 of 10
  3. Instruction Following−35.3%2 of 3
  4. Reasoning−41.8%4 of 6
Not rated6 capabilities

Too few results yet to rate Agentic, Safety, Math, Multimodal, Multilingual or Factuality.

Price

$15.00input$75.00outputper million tokens

From Anthropic's own price page · 2 providers tracked · All prices

Costs more than 97% of 330 priced models · 3:1 input-to-output blend, log scale

Evidence

121results on69benchmarks

  • 47 independently verified
  • 15 aggregator
  • 15 vendor-reported
  • 44 cross-referenced

From 27 sources · latest Oct 8, 2026 · How verification works

API features

Tool callingReasoning

As listed by OpenRouter

Research

179 papers reference Claude Opus 4

Claude Opus 4 benchmark results

121 results on 69 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

LimitedFull long context ranking

27.4% behind the leader2 of 3 ranked benchmarks measured

Show 1 more long context resultHide 1 long context result

Coding

LimitedFull coding ranking

34.0% behind the leader4 of 10 ranked benchmarks measured

Show 6 more coding resultsHide 6 coding results

Instruction Following

LimitedFull instruction following ranking

35.3% behind the leader2 of 3 ranked benchmarks measured

Show 3 more instruction following resultsHide 3 instruction following results

Reasoning

LimitedFull reasoning ranking

41.8% behind the leader4 of 6 ranked benchmarks measured

Show 12 more reasoning resultsHide 12 reasoning results

Multimodal

Not enough dataFull multimodal ranking

0 of 6 ranked benchmarks measured

Show 2 more multimodal resultsHide 2 multimodal results

Factuality

Not enough dataFull factuality ranking

0 of 4 ranked benchmarks measured

More results

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

Show 75 more resultsHide 75 results

Claude Opus 4: common questions

Who makes Claude Opus 4?

Claude Opus 4 is made by Anthropic.

When was Claude Opus 4 released?

Claude Opus 4 was released on May 22, 2025, according to Artificial Analysis.

What is Claude Opus 4 good at?

Claude Opus 4 is behind the leaders in long context, coding, instruction following, and reasoning. Too few results yet to rate agentic tasks, safety, math, multimodal tasks, multilingual tasks, or factuality.

How much does Claude Opus 4 cost?

Claude Opus 4 costs $15.00 per million input tokens and $75.00 per million output tokens, according to Anthropic's own price page. We track its price at 2 providers. At a mix of three input tokens to one output token, it costs more than 97% of the 330 priced models we track.

How many benchmarks has Claude Opus 4 been tested on?

We track 121 results for Claude Opus 4 on 69 benchmarks from 27 sources, 47 of them independently verified. The latest was recorded on Oct 8, 2026.

Which API features does Claude Opus 4 support?

OpenRouter lists tool calling and reasoning for Claude Opus 4.

About this record

Where Claude Opus 4's numbers come from, and every name it appears under.

Tracked since
Apr 27, 2026
Newest source mention
Sep 2, 2026

Where the results come from

Verification: 121 scores · 47 independently verified · 15 aggregator-attributed · 44 vendor cross-reference · 15 vendor-reported. How these tiers are assigned

From 27 sources on 17 sites. Hugging Face supplies 44 of them; the 47 independently verified results come from 13 sites. Bars are coloured by trust tier.

  • huggingface.co44
  • artificialanalysis.ai16
  • storage.googleapis.com11
  • api.llm-stats.com8
  • arcprize.org8
  • livecodebench.github.io8
  • raw.githubusercontent.com7
  • anthropic.com6
  • datasets-server.huggingface.co2
  • lmarena.ai2
  • matharena.ai2
  • swebench.com2
  • aider.chat1
  • epoch.ai1
  • labs.scale.com1
  • simple-bench.com1
  • www-cdn.anthropic.com1

Also known as

claude 4 opusclaude 4 opus (20250514, extended thinking)claude 4 opus (20250514)claude 4 opus (inspect)claude 4 opus (non-reasoning)claude 4 opus (reasoning)claude opus 4 (thinking 16k)claude opus 4 (thinking 1k)claude opus 4 (thinking 8k)Claude Opus 4-20250514 (no think)claude-4-opus-thinkingclaude-opus-4 (thinking)claude-opus-4-20250514claude-opus-4-20250514 (32k thinking)claude-opus-4-20250514-thinking-16kclaude-opus-4.0 (think)and 4 more