Anthropic: Claude Opus 5

Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual…

anthropic/claude-opus-5-20260723

Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis of charts and documents, complex office deliverables, and coordinating parallel subagents.

The model maintains strong instruction following and tool use across extended tasks, while remaining effective at lower effort settings for workloads that prioritize latency and token efficiency.

Specifications & capabilities

Input
text, image, file
Output
text
Context window · tokens
1000000
Published model ID
claude-opus-5
Capabilities
batch, computerUse, fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch
Description source ↗

Evaluations

21–40 / 224

LMArena

0.136

source id
lmarena
leaderboard name
LMArena Agent Bash Recovery Steps Overall
dimension
agentic
metric
Arena score
rank
2
sample size
60324
evaluated at
2026-10-08T00:00:00.000Z
source model id
Claude Opus 5 (Max)
confidence lower
0.1277785902477195
confidence upper
0.14362371389564313
Original result ↗

LMArena

1,530.983

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Mathematical
dimension
style
metric
Arena rating
rank
3
sample size
4082
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Opus 5 (High)
confidence lower
1520.5676430196656
confidence upper
1541.3974688481505
Original result ↗

LMArena

1,528.913

source id
lmarena
leaderboard name
LMArena Text Factuality Industry Life And Physical And Social Science
dimension
factuality
metric
Arena rating
rank
3
sample size
5387
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Opus 5 (Max)
confidence lower
1520.9643733856278
confidence upper
1536.8619636481121
Original result ↗

LMArena

1,527.252

source id
lmarena
leaderboard name
LMArena Text Industry Legal And Government
dimension
general
metric
Arena rating
rank
3
sample size
3045
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Opus 5 (Max)
confidence lower
1515.7602874065537
confidence upper
1538.7443514546367
Original result ↗

LMArena

1,526.327

source id
lmarena
leaderboard name
LMArena Text Industry Medicine And Healthcare
dimension
general
metric
Arena rating
rank
3
sample size
2690
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Opus 5 (Max)
confidence lower
1514.050950824234
confidence upper
1538.602549666775
Original result ↗

LMArena

1,521.404

source id
lmarena
leaderboard name
LMArena Text Style Control Math
dimension
style
metric
Arena rating
rank
3
sample size
3494
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Opus 5 (High)
confidence lower
1510.5043361276612
confidence upper
1532.303883504675
Original result ↗

LMArena

1,515.551

source id
lmarena
leaderboard name
LMArena Text Factuality Math
dimension
factuality
metric
Arena rating
rank
3
sample size
2961
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Opus 5 (High)
confidence lower
1505.2003392454326
confidence upper
1525.9016653314818
Original result ↗

LMArena

1,508.906

source id
lmarena
leaderboard name
LMArena Text Factuality Industry Mathematical
dimension
factuality
metric
Arena rating
rank
3
sample size
1674
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Opus 5 (Max)
confidence lower
1496.064313107413
confidence upper
1521.7483804372405
Original result ↗

LMArena

1,501.186

source id
lmarena
leaderboard name
LMArena Text Korean
dimension
general
metric
Arena rating
rank
3
sample size
1286
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Opus 5 (High)
confidence lower
1483.0281002242987
confidence upper
1519.3445088458623
Original result ↗

LMArena

1,498.855

source id
lmarena
leaderboard name
LMArena Text Industry Business And Management And Financial Operations
dimension
general
metric
Arena rating
rank
3
sample size
6622
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Opus 5 (Max)
confidence lower
1490.702644121069
confidence upper
1507.0064574643045
Original result ↗

LMArena

1,364.342

source id
lmarena
leaderboard name
LMArena Vision Style Control Chinese
dimension
multimodal
metric
Arena rating
rank
3
sample size
1148
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Opus 5 (High)
confidence lower
1344.9603448923694
confidence upper
1383.723538023496
Original result ↗

LMArena

1,552.321

source id
lmarena
leaderboard name
LMArena Text Expert
dimension
general
metric
Arena rating
rank
4
sample size
3686
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Opus 5 (Max)
confidence lower
1541.7185088466176
confidence upper
1562.9225052359666
Original result ↗

LMArena

1,539

source id
lmarena
leaderboard name
LMArena Text Industry Mathematical
dimension
general
metric
Arena rating
rank
4
sample size
1977
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Opus 5 (Max)
confidence lower
1525.001248509166
confidence upper
1552.9982519746168
Original result ↗

LMArena

1,532.513

source id
lmarena
leaderboard name
LMArena Text Industry Life And Physical And Social Science
dimension
general
metric
Arena rating
rank
4
sample size
5927
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Opus 5 (Max)
confidence lower
1524.0813670099024
confidence upper
1540.9446744085744
Original result ↗

LMArena

1,530.766

source id
lmarena
leaderboard name
LMArena Text Math
dimension
general
metric
Arena rating
rank
4
sample size
1702
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Opus 5 (Max)
confidence lower
1516.1347885197804
confidence upper
1545.3966630509224
Original result ↗

LMArena

1,522.162

source id
lmarena
leaderboard name
LMArena Text Factuality Industry Legal And Government
dimension
factuality
metric
Arena rating
rank
4
sample size
5384
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Opus 5 (High)
confidence lower
1513.7116975252322
confidence upper
1530.6131871595028
Original result ↗

LMArena

1,522.109

source id
lmarena
leaderboard name
LMArena Text Polish
dimension
general
metric
Arena rating
rank
4
sample size
577
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Opus 5 (Max)
confidence lower
1497.7873300274546
confidence upper
1546.431457940469
Original result ↗

LMArena

1,521.193

source id
lmarena
leaderboard name
LMArena Text Industry Legal And Government
dimension
general
metric
Arena rating
rank
4
sample size
6205
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Opus 5 (High)
confidence lower
1512.5731079372838
confidence upper
1529.8128592739426
Original result ↗

OpenRouter Benchmarks

77.267%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Google
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
4
sample size
1500
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
30
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
tau_bench_verified_airline
name
tau2-bench Verified Airline
record_kind
aggregate
provider_name
Google
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T12:26:08.030Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
tau2-bench Verified Airline · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
1500
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.7726666333333335
accuracy_std_dev
0.022400415672457697
cost_per_task_usd
0.49225354466666665
output_tokens_per_task
7051.117333333334
latency_seconds_per_task
105.640478
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
36
benchmark_evaluation
true
openrouter_permaslug
anthropic/claude-opus-5-20260723
source model id
anthropic/claude-opus-5-20260723
Original result ↗

OpenRouter Benchmarks

77%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Claude Platform on AWS
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
4
sample size
500
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
10
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
tau_bench_verified_airline
name
tau2-bench Verified Airline
record_kind
aggregate
provider_name
Claude Platform on AWS
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T11:40:34.382Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
tau2-bench Verified Airline · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
500
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.77
accuracy_std_dev
0.01639789959720451
cost_per_task_usd
0.464249572
output_tokens_per_task
7042.312
latency_seconds_per_task
116.89473
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
12
benchmark_evaluation
true
openrouter_permaslug
anthropic/claude-opus-5-20260723
source model id
anthropic/claude-opus-5-20260723
Original result ↗

Published prices

1–20 / 90

claude-opus-5 ↗

$0.33

Inference provider
cheaperInference
Platform
Cheaper Inference
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
zdr
false
protocol
chat_completions
service_tier
standard
Billing label
Cached input tokens (per 1M)

claude-opus-5 ↗

$6.50

Inference provider
cheaperInference
Platform
Cheaper Inference
Unit
cache_write_1h_tokens_per_million
Currency
USD
Billing conditions
zdr
false
protocol
chat_completions
service_tier
standard
Billing label
Cache write, 1 hour (per 1M)

claude-opus-5 ↗

$4.06

Inference provider
cheaperInference
Platform
Cheaper Inference
Unit
cache_write_tokens_per_million
Currency
USD
Billing conditions
zdr
false
protocol
chat_completions
service_tier
standard
Billing label
Cache write, 5 minutes (per 1M)

claude-opus-5 ↗

$3.25

Inference provider
cheaperInference
Platform
Cheaper Inference
Unit
input_tokens_per_million
Currency
USD
Billing conditions
zdr
false
protocol
chat_completions
service_tier
standard
Billing label
Input tokens (per 1M)

claude-opus-5 ↗

$16.25

Inference provider
cheaperInference
Platform
Cheaper Inference
Unit
output_tokens_per_million
Currency
USD
Billing conditions
zdr
false
protocol
chat_completions
service_tier
standard
Billing label
Output tokens (per 1M)

anthropic/claude-opus-5 ↗

$0.50

Inference provider
cloudflareWorkersAI
Platform
Anthropic
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
Billing label
Cached input tokens (per 1M)
Pricing via
Cloudflare AI Gateway

anthropic/claude-opus-5 ↗

$6.25

Inference provider
cloudflareWorkersAI
Platform
Anthropic
Unit
cache_write_tokens_per_million
Currency
USD
Billing conditions
Billing label
Cache creation tokens (per 1M)
Pricing via
Cloudflare AI Gateway

anthropic/claude-opus-5 ↗

$5.00

Inference provider
cloudflareWorkersAI
Platform
Anthropic
Unit
input_tokens_per_million
Currency
USD
Billing conditions
Billing label
Input tokens (per 1M)
Pricing via
Cloudflare AI Gateway

anthropic/claude-opus-5 ↗

$25.00

Inference provider
cloudflareWorkersAI
Platform
Anthropic
Unit
output_tokens_per_million
Currency
USD
Billing conditions
Billing label
Output tokens (per 1M)
Pricing via
Cloudflare AI Gateway

anthropic/claude-opus-5 ↗

$0.50

Inference provider
openRouter
Platform
OpenRouter
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions

anthropic/claude-opus-5 ↗

$10.00

Inference provider
openRouter
Platform
OpenRouter
Unit
cache_write_1h_tokens_per_million
Currency
USD
Billing conditions

anthropic/claude-opus-5 ↗

$6.25

Inference provider
openRouter
Platform
OpenRouter
Unit
cache_write_tokens_per_million
Currency
USD
Billing conditions

anthropic/claude-opus-5 ↗

$5.00

Inference provider
openRouter
Platform
OpenRouter
Unit
input_tokens_per_million
Currency
USD
Billing conditions

anthropic/claude-opus-5 ↗

$25.00

Inference provider
openRouter
Platform
OpenRouter
Unit
output_tokens_per_million
Currency
USD
Billing conditions

Provider specifications & access

1–8 / 8

Claude Opus 5 ↗

source model id
anthropic.claude-opus-5
hosting
bedrock-managed
platforms
  • Amazon Bedrock
architecture
input_modalities
  • text
  • image
output_modalities
  • text
capabilities

    Claude Opus 5 ↗

    source model id
    anthropic/claude-opus-5
    hosting
    third-party
    platforms
    • Anthropic
    context length
    1000000
    max output tokens
    128000
    architecture
    input_modalities
    • text
    output_modalities
    • text
    capabilities
    • reasoning

    Claude Opus 5 ↗

    source model id
    anthropic/claude-opus-5
    hosting
    vercel-gateway
    platforms
    • Vercel AI Gateway
    context length
    1000000
    max output tokens
    128000
    architecture
    input_modalities
    • text
    • image
    • pdf
    output_modalities
    • text
    capabilities
    • promptCaching
    • reasoning
    • structuredOutputs
    • toolCalling
    • visionInput
    • webSearch
    regions
    • au
    • eu
    • us

    Claude Opus 5 · azureml-anthropic v1 ↗

    source model id
    azureml-anthropic/claude-opus-5@1
    hosting
    foundry-managed-compute
    platforms
    • Microsoft Foundry
    context length
    1000000
    max output tokens
    128000
    architecture
    input_modalities
    • text
    • image
    • code
    output_modalities
    • text
    capabilities
    • reasoning
    • toolCalling

    Claude Opus 5 · azureml-anthropic v2 ↗

    source model id
    azureml-anthropic/claude-opus-5@2
    hosting
    foundry-managed-compute
    platforms
    • Microsoft Foundry
    context length
    1000000
    max output tokens
    128000
    architecture
    input_modalities
    • text
    • image
    • code
    output_modalities
    • text
    capabilities
    • reasoning
    • toolCalling

    claude-opus-5 ↗

    source model id
    claude-opus-5
    hosting
    gateway
    platforms
    • Cheaper Inference
    context length
    1000000
    max output tokens
    128000
    architecture
    input_modalities
    • text
    • image
    output_modalities
    • text
    capabilities
    • reasoning
    • structuredOutputs
    • toolCalling
    • visionInput
    • webSearch

    anthropic ↗

    source model id
    Claude Opus 5
    hosting
    copilot-subscription
    platforms
    • GitHub Copilot
    architecture
    license
    CC-BY-4.0
    attribution
    GitHub and github/docs contributors
    plans
    max
    true
    pro
    false
    business
    true
    pro_plus
    true
    enterprise
    true
    clients
    vs
    true
    cli
    true
    xcode
    true
    dotcom
    true
    vscode
    true
    eclipse
    true
    jetbrains
    true
    auto selection
    app
    true
    cli
    true
    chat
    true
    cloud_agent
    true
    access scope
    Published plan/client flags; account settings, organization policy and additional access conditions apply
    availability
    supported
    release status
    GA
    billing scope
    Copilot subscription usage; not an unconditional inference API rate
    billing rates
    • unit
      tokens_per_million
      input
      5
      output
      25
      currency
      USD
      original
      input
      $5.00
      model
      Claude Opus 5
      output
      $25.00
      category
      Powerful
      provider
      anthropic
      cache_write
      $6.25
      cached_input
      $0.50
      release_status
      GA
      cache_write
      6.25
      cached_input
      0.5
      footnote_restrictions
      false
      requires_subscription
      true
    comparison
    name
    Claude Opus 5
    excels_at
    Complex problem-solving challenges, sophisticated reasoning
    task_area
    Deep reasoning and debugging
    further_reading
    [Claude Opus 5 model card](https://www-cdn.anthropic.com/c5fbac3f0b1280a933ebd26d3cb8bb9f5bdeaf48/Claude%20Opus%205%20System%20Card.pdf)

    Claude Opus 5 on Google Cloud ↗

    source model id
    publishers/anthropic/models/claude-opus-5@default
    hosting
    vertex-managed
    platforms
    • Google Cloud Vertex AI
    max input tokens
    1000000
    max output tokens
    128000
    architecture
    input_modalities
    • file
    • image
    • text
    output_modalities
    • text
    capabilities
    • batch
    • computerUse
    • multimodal
    • promptCaching
    • toolCalling
    • visionInput
    • webSearch

    Safety assessments

    1–1 / 1

    Foundation Model Transparency Index 2025 ↗

    46 / 100

    source id
    stanfordFMTI
    canonical model id
    anthropic/claude-opus-5-20260723
    taxonomy
    transparency
    hazard category
    transparency
    hazard name
    Organization transparency
    policy area
    Anthropic
    assessment type
    organization-level disclosure
    metric
    disclosure_score
    result label
    46 / 100
    sample size
    100
    updated at
    2026-11-09T18:08:05.227Z

    Source specification observations

    1–17 / 17

    azureFoundry ↗

    field
    context_length
    value
    1000000
    normalized value
    1000000
    scope
    source-model
    source id
    azureFoundry
    confidence
    1

    azureFoundry ↗

    field
    context_length
    value
    1000000
    normalized value
    1000000
    scope
    source-model
    source id
    azureFoundry
    confidence
    1

    cloudflareWorkersAI ↗

    field
    context_length
    value
    1000000
    normalized value
    1000000
    scope
    source-model
    source id
    cloudflareWorkersAI
    confidence
    1

    openRouter ↗

    field
    context_length
    value
    1000000
    normalized value
    1000000
    scope
    source-model
    source id
    openRouter
    confidence
    1

    openRouter ↗

    field
    context_length
    value
    1000000
    normalized value
    1000000
    scope
    source-model
    source id
    openRouter
    confidence
    1

    vercelAIGatewayCatalog ↗

    field
    context_length
    value
    1000000
    normalized value
    1000000
    scope
    source-model
    source id
    vercelAIGatewayCatalog
    confidence
    1

    vercelAIGatewayCatalog ↗

    field
    knowledge_cutoff
    reported field
    knowledge_cutoff
    value
    2026-05
    normalized value
    2026-05
    precision
    month
    scope
    source-model
    source id
    vercelAIGatewayCatalog
    confidence
    1

    vertexAI ↗

    field
    max_input_tokens
    value
    1000000
    normalized value
    1000000
    scope
    source-model
    source id
    vertexAI
    confidence
    1

    azureFoundry ↗

    field
    max_output_tokens
    value
    128000
    normalized value
    128000
    scope
    source-model
    source id
    azureFoundry
    confidence
    1

    azureFoundry ↗

    field
    max_output_tokens
    value
    128000
    normalized value
    128000
    scope
    source-model
    source id
    azureFoundry
    confidence
    1

    cloudflareWorkersAI ↗

    field
    max_output_tokens
    value
    128000
    normalized value
    128000
    scope
    source-model
    source id
    cloudflareWorkersAI
    confidence
    1

    openRouter ↗

    field
    max_output_tokens
    value
    128000
    normalized value
    128000
    scope
    source-model
    source id
    openRouter
    confidence
    1

    openRouter ↗

    field
    max_output_tokens
    value
    128000
    normalized value
    128000
    scope
    source-model
    source id
    openRouter
    confidence
    1

    vercelAIGatewayCatalog ↗

    field
    max_output_tokens
    value
    128000
    normalized value
    128000
    scope
    source-model
    source id
    vercelAIGatewayCatalog
    confidence
    1

    vertexAI ↗

    field
    max_output_tokens
    value
    128000
    normalized value
    128000
    scope
    source-model
    source id
    vertexAI
    confidence
    1

    azureFoundry ↗

    field
    knowledge_cutoff
    reported field
    training_data_cutoff
    value
    January 2026
    normalized value
    2026-01
    precision
    month
    scope
    source-model
    source id
    azureFoundry
    confidence
    1

    azureFoundry ↗

    field
    knowledge_cutoff
    reported field
    training_data_cutoff
    value
    January 2026
    normalized value
    2026-01
    precision
    month
    scope
    source-model
    source id
    azureFoundry
    confidence
    1

    Original sources

    1–20 / 24

    Anthropic · Model reference ↗

    Google Cloud · Model page ↗

    Microsoft Foundry · Model page ↗

    Microsoft Foundry · Model page ↗

    OpenRouter · Model page ↗

    OpenRouter · Model page ↗

    Vercel AI Gateway · Model page ↗

    GitHub · Documentation ↗

    Google Cloud · Documentation ↗

    Microsoft Foundry · Model documentation ↗

    GitHub · Source snapshot ↗

    api.cheaperinference.com · Source snapshot ↗

    Amazon Web Services · Model page ↗

    Amazon Bedrock · Model documentation ↗

    Amazon Web Services · Catalog ↗

    Cloudflare AI · Catalog ↗

    Epoch AI · Catalog ↗

    GitHub · Catalog ↗

    Google Cloud · Catalog ↗

    LMArena · Catalog ↗

    Source links

    1–13 / 13

    Explore more models

    Models

    Loading
    EVIDENCE / COMPARISON

    Benchmarks

    Explore every benchmark

    Loading

    These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

    Install TensorTrace