Anthropic: Claude Sonnet 4.5

Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-be…

anthropic/claude-4.5-sonnet-20250929

Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with improvements across system design, code security, and specification adherence. The model is designed for extended autonomous operation, maintaining task continuity across sessions and providing fact-based progress tracking.

Sonnet 4.5 also introduces stronger agentic capabilities, including improved tool orchestration, speculative parallel execution, and more efficient context and memory management. With enhanced context tracking and awareness of token usage across tool calls, it is particularly well-suited for multi-context and long-running workflows. Use cases span software engineering, cybersecurity, financial analysis, research agents, and other domains requiring sustained reasoning and tool use.

Specifications & capabilities

Input
text, image, file
Output
text
Context window · tokens
1000000
Published model ID
claude-sonnet-4-5-20250929
Capabilities
fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput
Description source ↗

Evaluations

41–60 / 125

BFCL

16%

source id
bfcl
leaderboard name
BFCL Web Search
dimension
agentic
metric
Web-search accuracy
rank
47
Original result ↗

LMArena

1,484.837

source id
lmarena
leaderboard name
LMArena Text Coding
dimension
general
metric
Arena rating
rank
48
sample size
19630
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1479.8482541036008
confidence upper
1489.8249154252724
Original result ↗

LMArena

1,477.318

source id
lmarena
leaderboard name
LMArena Text Style Control Multi Turn
dimension
style
metric
Arena rating
rank
48
sample size
14403
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1471.6708712402556
confidence upper
1482.965616062414
Original result ↗

LMArena

1,443.988

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Entertainment And Sports And Media
dimension
style
metric
Arena rating
rank
48
sample size
15650
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1438.53103889378
confidence upper
1449.4446204649603
Original result ↗

LMArena

1,454.09

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Writing And Literature And Language
dimension
style
metric
Arena rating
rank
49
sample size
18864
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1449.0719538066758
confidence upper
1459.1086730224258
Original result ↗

LMArena

1,475.054

source id
lmarena
leaderboard name
LMArena Text Factuality French
dimension
factuality
metric
Arena rating
rank
50
sample size
1288
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1458.7974018232967
confidence upper
1491.3099902434687
Original result ↗

LMArena

1,461.975

source id
lmarena
leaderboard name
LMArena Text Style Control Instruction Following
dimension
style
metric
Arena rating
rank
50
sample size
24184
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1457.3650869724675
confidence upper
1466.5848043347723
Original result ↗

LMArena

1,428.683

source id
lmarena
leaderboard name
LMArena Text Industry Entertainment And Sports And Media
dimension
general
metric
Arena rating
rank
50
sample size
15650
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1423.239578992808
confidence upper
1434.1269357719063
Original result ↗

LMArena

1,495.405

source id
lmarena
leaderboard name
LMArena Text Factuality Hard Prompts English
dimension
factuality
metric
Arena rating
rank
51
sample size
14569
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1489.966512594584
confidence upper
1500.84274761356
Original result ↗

LMArena

1,470.215

source id
lmarena
leaderboard name
LMArena Text Hard Prompts English
dimension
general
metric
Arena rating
rank
52
sample size
21132
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1465.357666800857
confidence upper
1475.0719092984039
Original result ↗

LMArena

1,442.02

source id
lmarena
leaderboard name
LMArena Text Industry Writing And Literature And Language
dimension
general
metric
Arena rating
rank
53
sample size
18864
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1437.0182991556599
confidence upper
1447.0224716436896
Original result ↗

LMArena

1,512.172

source id
lmarena
leaderboard name
LMArena Text Style Control Coding
dimension
style
metric
Arena rating
rank
54
sample size
19630
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1507.1502590119212
confidence upper
1517.1931653359075
Original result ↗

LMArena

1,497.433

source id
lmarena
leaderboard name
LMArena Text Factuality Industry Software And It Services
dimension
factuality
metric
Arena rating
rank
54
sample size
23333
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1493.0285392132419
confidence upper
1501.8380903303275
Original result ↗

LMArena

1,488.917

source id
lmarena
leaderboard name
LMArena Text Factuality Expert
dimension
factuality
metric
Arena rating
rank
54
sample size
3675
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1479.3918624962903
confidence upper
1498.4424905823819
Original result ↗

LMArena

1,406.181

source id
lmarena
leaderboard name
LMArena Text Factuality Polish
dimension
factuality
metric
Arena rating
rank
54
sample size
1338
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1390.4142994343529
confidence upper
1421.9480987469838
Original result ↗

LMArena

1,480.476

source id
lmarena
leaderboard name
LMArena Text Factuality Hard Prompts
dimension
factuality
metric
Arena rating
rank
55
sample size
44654
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1477.1462123579186
confidence upper
1483.8054912032908
Original result ↗

LMArena

1,459.758

source id
lmarena
leaderboard name
LMArena Text Factuality Industry Business And Management And Financial Operations
dimension
factuality
metric
Arena rating
rank
55
sample size
9753
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1453.229083704362
confidence upper
1466.2867611366096
Original result ↗

LMArena

1,489.237

source id
lmarena
leaderboard name
LMArena Text Style Control Hard Prompts English
dimension
style
metric
Arena rating
rank
56
sample size
21132
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1484.359582257728
confidence upper
1494.113974387665
Original result ↗

LMArena

1,461.97

source id
lmarena
leaderboard name
LMArena Text Hard Prompts
dimension
general
metric
Arena rating
rank
56
sample size
47965
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1458.3759838592232
confidence upper
1465.564431671025
Original result ↗

LMArena

1,472.586

source id
lmarena
leaderboard name
LMArena Text Industry Software And It Services
dimension
general
metric
Arena rating
rank
58
sample size
30110
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1468.3725404130298
confidence upper
1476.7996932726955
Original result ↗

Published prices

1–16 / 16

anthropic/claude-sonnet-4.5 ↗

$0.30

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-sonnet-4.5 ↗

$3.75

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-sonnet-4.5 ↗

$3.00

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-sonnet-4.5 ↗

$15.00

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

Provider specifications & access

1–3 / 3

Claude Sonnet 4.5 ↗

source model id
anthropic/claude-sonnet-4.5
hosting
third-party
platforms
  • Anthropic
context length
200000
max output tokens
8192
architecture
input_modalities
  • text
output_modalities
  • text
capabilities
  • reasoning

Claude Sonnet 4.5 ↗

source model id
anthropic.claude-sonnet-4-5-20250929-v1:0
hosting
bedrock-managed
platforms
  • Amazon Bedrock
architecture
input_modalities
  • text
  • image
output_modalities
  • text
capabilities

    Claude Sonnet 4.5 · azureml-anthropic v20250929 ↗

    source model id
    azureml-anthropic/claude-sonnet-4-5@20250929
    hosting
    foundry-managed-compute
    platforms
    • Microsoft Foundry
    context length
    200000
    max output tokens
    64000
    architecture
    input_modalities
    • text
    • image
    • code
    output_modalities
    • text
    capabilities
    • reasoning
    • toolCalling

    Safety assessments

    1–1 / 1

    Foundation Model Transparency Index 2025 ↗

    46 / 100

    source id
    stanfordFMTI
    canonical model id
    anthropic/claude-4.5-sonnet-20250929
    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

    1–11 / 11

    azureFoundry ↗

    field
    context_length
    value
    200000
    normalized value
    200000
    scope
    source-model
    source id
    azureFoundry
    confidence
    1

    cloudflareWorkersAI ↗

    field
    context_length
    value
    200000
    normalized value
    200000
    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

    openRouter ↗

    field
    knowledge_cutoff
    reported field
    knowledge_cutoff
    value
    2025-01-31
    normalized value
    2025-01-31
    precision
    day
    scope
    source-model
    source id
    openRouter
    confidence
    1

    openRouter ↗

    field
    knowledge_cutoff
    reported field
    knowledge_cutoff
    value
    2025-01-31
    normalized value
    2025-01-31
    precision
    day
    scope
    source-model
    source id
    openRouter
    confidence
    1

    azureFoundry ↗

    field
    max_output_tokens
    value
    64000
    normalized value
    64000
    scope
    source-model
    source id
    azureFoundry
    confidence
    1

    cloudflareWorkersAI ↗

    field
    max_output_tokens
    value
    8192
    normalized value
    8192
    scope
    source-model
    source id
    cloudflareWorkersAI
    confidence
    1

    openRouter ↗

    field
    max_output_tokens
    value
    64000
    normalized value
    64000
    scope
    source-model
    source id
    openRouter
    confidence
    1

    openRouter ↗

    field
    max_output_tokens
    value
    64000
    normalized value
    64000
    scope
    source-model
    source id
    openRouter
    confidence
    1

    azureFoundry ↗

    field
    knowledge_cutoff
    reported field
    training_data_cutoff
    value
    July 2025
    normalized value
    2025-07
    precision
    month
    scope
    source-model
    source id
    azureFoundry
    confidence
    1

    Original sources

    1–19 / 19

    Anthropic · Model reference ↗

    Microsoft Foundry · Model page ↗

    OpenRouter · Model page ↗

    OpenRouter · Model page ↗

    Microsoft Foundry · Model documentation ↗

    GitHub · Source snapshot ↗

    Amazon Web Services · Model page ↗

    Amazon Bedrock · Model documentation ↗

    Amazon Web Services · Catalog ↗

    Cloudflare AI · Catalog ↗

    Epoch AI · Catalog ↗

    GitHub · Catalog ↗

    LMArena · Catalog ↗

    Microsoft Foundry · Catalog ↗

    OpenRouter · Catalog ↗

    OpenRouter · Catalog ↗

    Vercel AI Gateway · Catalog ↗

    gorilla.cs.berkeley.edu · Catalog ↗

    www.swebench.com · 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