Anthropic model product
Claude Opus 4
Claude Opus 4 is an Anthropic large language model in the Claude 4 family for coding, advanced reasoning, and extended tool-using tasks.
Updated Oct 23, 2026. Default version: Claude Opus 4
LLMBoard Score44.6Claude Opus 4
Coverage20%9 benchmark families
Context window200KTokens
Official input priceN/AOfficial price unavailable
Claude Opus 4 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Claude Opus 4 Benchmark Results
Benchmark scores for Claude Opus 4.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkMMMU (validation) | Score76.50% | Rank03 | Participants4 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkTAU-bench Retail | Score81.40% | Rank03 | Participants25 | Percentile91.67% | EvidenceC | Evaluated |
| BenchmarkTAU-bench Airline | Score59.60% | Rank08 | Participants23 | Percentile68.18% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench | Score39.20% | Rank10 | Participants25 | Percentile62.50% | EvidenceC | Evaluated |
| BenchmarkARC-AGI v2 | Score8.60% | Rank16 | Participants19 | Percentile16.67% | EvidenceB | Evaluated |
| BenchmarkMMMLU | Score88.80% | Rank16 | Participants51 | Percentile70.00% | EvidenceC | Evaluated |
| BenchmarkLM Arena Search Style Control | Score1,151.84 rating | Rank29 | Participants33 | Percentile12.50% | EvidenceA | Evaluated |
| BenchmarkLM Arena Search Factuality | Score1,139.60 rating | Rank30 | Participants33 | Percentile9.38% | EvidenceA | Evaluated |
| BenchmarkLM Arena Search | Score1,127.43 rating | Rank33 | Participants33 | Percentile0.00% | EvidenceA | Evaluated |
| BenchmarkSWE-Bench Verified | Score72.50% | Rank59 | Participants120 | Percentile51.26% | EvidenceC | Evaluated |
| BenchmarkLM Arena Vision Style Control | Score1,207.50 rating | Rank70 | Participants113 | Percentile38.39% | EvidenceA | Evaluated |
| BenchmarkLM Arena Vision | Score1,191.76 rating | Rank79 | Participants113 | Percentile30.36% | EvidenceA | Evaluated |
| BenchmarkAIME 2025 | Score75.50% | Rank84 | Participants122 | Percentile31.41% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,426.30 rating | Rank91 | Participants218 | Percentile58.53% | EvidenceA | Evaluated |
| BenchmarkGPQA | Score79.60% | Rank105 | Participants256 | Percentile59.22% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text | Score1,377.13 rating | Rank126 | Participants218 | Percentile42.40% | EvidenceA | Evaluated |
Claude Opus 4 Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenavision style control | Categorycreative writing | Rank08 | Rating / score1,258.38 | Votes192 | ObservationsN/A | Result date |
| Arenavision | Categorycreative writing | Rank09 | Rating / score1,253.43 | Votes192 | ObservationsN/A | Result date |
| Arenasearch style control | Categoryoverall | Rank29 | Rating / score1,151.84 | Votes31,506 | ObservationsN/A | Result date |
| Arenasearch factuality | Categoryoverall | Rank30 | Rating / score1,139.60 | Votes14,486 | ObservationsN/A | Result date |
| Arenasearch | Categoryoverall | Rank33 | Rating / score1,127.43 | Votes31,506 | ObservationsN/A | Result date |
| Arenatext style control | Categorylonger query | Rank48 | Rating / score1,466.27 | Votes6,966 | ObservationsN/A | Result date |
| Arenatext style control | Categorycreative writing | Rank50 | Rating / score1,432.68 | Votes4,461 | ObservationsN/A | Result date |
| Arenatext style control | Categoryinstruction following | Rank52 | Rating / score1,444.35 | Votes9,152 | ObservationsN/A | Result date |
| Arenatext style control | Categorygerman | Rank55 | Rating / score1,450.78 | Votes955 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry entertainment and sports and media | Rank56 | Rating / score1,421.78 | Votes6,295 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry writing and literature and language | Rank56 | Rating / score1,431.41 | Votes7,820 | ObservationsN/A | Result date |
| Arenatext style control | Categorycoding | Rank58 | Rating / score1,498.34 | Votes6,596 | ObservationsN/A | Result date |
| Arenatext style control | Categoryrussian | Rank66 | Rating / score1,440.62 | Votes2,552 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhomework | Rank67 | Rating / score1,241.74 | Votes306 | ObservationsN/A | Result date |
| Arenavision | Categoryhomework | Rank70 | Rating / score1,227.93 | Votes306 | ObservationsN/A | Result date |
| Arenavision style control | Categoryocr | Rank70 | Rating / score1,218.14 | Votes835 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank70 | Rating / score1,207.50 | Votes1,290 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank74 | Rating / score1,385.93 | Votes794 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank75 | Rating / score1,432.36 | Votes861 | ObservationsN/A | Result date |
| Arenavision | Categoryocr | Rank77 | Rating / score1,196.54 | Votes835 | ObservationsN/A | Result date |
| Arenatext style control | Categoryhard prompts | Rank78 | Rating / score1,456.96 | Votes16,190 | ObservationsN/A | Result date |
| Arenatext style control | Categoryjapanese | Rank78 | Rating / score1,385.52 | Votes832 | ObservationsN/A | Result date |
| Arenavision style control | Categoryenglish | Rank78 | Rating / score1,196.02 | Votes954 | ObservationsN/A | Result date |
| Arenatext style control | Categoryhard prompts english | Rank79 | Rating / score1,460.33 | Votes7,199 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank79 | Rating / score1,191.76 | Votes1,290 | ObservationsN/A | Result date |
| Arenatext style control | Categorymulti turn | Rank80 | Rating / score1,439.13 | Votes6,041 | ObservationsN/A | Result date |
| Arenavision style control | Categorydiagram | Rank80 | Rating / score1,207.88 | Votes279 | ObservationsN/A | Result date |
| Arenatext | Categorylonger query | Rank81 | Rating / score1,422.03 | Votes6,966 | ObservationsN/A | Result date |
| Arenavision | Categorydiagram | Rank81 | Rating / score1,179.21 | Votes279 | ObservationsN/A | Result date |
| Arenatext style control | Categorypolish | Rank83 | Rating / score1,419.78 | Votes3,571 | ObservationsN/A | Result date |
Claude Opus 4 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- From $13 input, $64 output per 1M via Poe
- Tracked offerings
- 8
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderPoe | Provider model IDanthropic/claude-opus-4 | Regionglobal | Input / 1M$13 | Output / 1M$64 | Context192.5K | Updated |
| ProviderJiekou.AI | Provider model IDclaude-opus-4-20250514 | Regionglobal | Input / 1M$13.5 | Output / 1M$67.5 | Context200K | Updated |
| ProviderVertex | Provider model IDclaude-opus-4@20250514 | Regionglobal | Input / 1M$15 | Output / 1M$75 | Context200K | Updated |
| ProviderVertex (Anthropic) | Provider model IDclaude-opus-4@20250514 | Regionglobal | Input / 1M$15 | Output / 1M$75 | Context200K | Updated |
| ProviderMerge Gateway | Provider model IDanthropic/claude-opus-4-20250514 | Regionglobal | Input / 1M$15 | Output / 1M$75 | Context200K | Updated |
| ProviderDigitalOcean | Provider model IDanthropic-claude-opus-4 | Regionglobal | Input / 1M$15 | Output / 1M$75 | Context200K | Updated |
| ProviderZenMux | Provider model IDanthropic/claude-opus-4 | Regionglobal | Input / 1M$15 | Output / 1M$75 | Context200K | Updated |
| ProviderAbacus | Provider model IDclaude-opus-4-20250514 | Regionglobal | Input / 1M$15 | Output / 1M$75 | Context200K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Claude Opus 4 Runtime Performance
Provider-specific output speed and catalog latency for Claude Opus 4. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderAnthropic | Output Speed100.00 tok/s | Catalog Latency0.50 s | Max Input200K | Max Output32K | Updated |
| ProviderGoogle | Output Speed42.00 tok/s | Catalog Latency0.40 s | Max Input200K | Max Output128K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Claude Opus 4 Specifications
Technical details for the model's default version.
- Version
- Claude Opus 4
- Released
- May 22, 2025
- Knowledge cutoff
- Unknown
- Parameters
- N/A
- Context window
- 200K
- Max output
- 128K
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Claude Opus 4 Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionClaude Opus 4 | Released | LLMBoard44.61 | ParametersN/A | Context200K | Max output128K | Open weightsNo | LicenseProprietary |
Models similar to Claude Opus 4
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AN
Claude Haiku 4.5
Anthropic
AN
Claude Opus 4.1
Anthropic
AN
Claude Sonnet 4
Anthropic
AN
Claude Sonnet 3.7
Anthropic
AN
Claude Sonnet 4.5
Anthropic
AN
Claude Sonnet 3.5
Anthropic
What is Claude Opus 4?
Key information about Claude Opus 4 and its available data.
Claude Opus 4 is a large language model from Anthropic and part of the Claude 4 family. It supports coding, advanced reasoning, web search and other tool use during extended tasks, parallel tool execution, and improved memory capabilities.
Data as of 2026-10-22.
FAQ
Common questions about Claude Opus 4.
When was Claude Opus 4 released?
Claude Opus 4's default version was released on May 22, 2025.
How much does Claude Opus 4 cost?
No official standard PAYG price is currently available for Claude Opus 4. The lowest tracked third-party offer starts at $13 input and $64 output via Poe.
Who created Claude Opus 4?
Claude Opus 4 was created by Anthropic.
What is the context window for Claude Opus 4?
The default version has a 200K token context window.
Is Claude Opus 4 open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Claude Opus 4?
8 provider offerings are linked to the default version.