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

61–80 / 125

LMArena

1,439.712

source id
lmarena
leaderboard name
LMArena Text Industry Business And Management And Financial Operations
dimension
general
metric
Arena rating
rank
58
sample size
15760
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1434.3685173329527
confidence upper
1445.0549039762427
Original result ↗

OpenRouter Benchmarks

72.2%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · auto-routing
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
59
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
auto-routing
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T12:49:56.822Z
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
0.722
accuracy_std_dev
0.030265381765310677
cost_per_task_usd
0.332162946
output_tokens_per_task
10350.054
latency_seconds_per_task
207.98325200000002
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
128
benchmark_evaluation
true
openrouter_permaslug
anthropic/claude-4.5-sonnet-20250929
source model id
anthropic/claude-4.5-sonnet-20250929
Original result ↗

LMArena

1,460.276

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Business And Management And Financial Operations
dimension
style
metric
Arena rating
rank
60
sample size
15760
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1454.9061302472703
confidence upper
1465.644926421134
Original result ↗

LMArena

1,459.585

source id
lmarena
leaderboard name
LMArena Text Factuality Russian
dimension
factuality
metric
Arena rating
rank
60
sample size
5603
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1451.6853503287446
confidence upper
1467.484464481469
Original result ↗

LMArena

1,482.966

source id
lmarena
leaderboard name
LMArena Text Style Control Hard Prompts
dimension
style
metric
Arena rating
rank
62
sample size
47965
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1479.3528853837672
confidence upper
1486.5791850375945
Original result ↗

LMArena

1,472.847

source id
lmarena
leaderboard name
LMArena Text Expert
dimension
general
metric
Arena rating
rank
62
sample size
6090
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1464.9920617011835
confidence upper
1480.7013589424032
Original result ↗

LMArena

1,466.703

source id
lmarena
leaderboard name
LMArena Text Factuality Industry Legal And Government
dimension
factuality
metric
Arena rating
rank
62
sample size
3499
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1456.0740530185547
confidence upper
1477.332386354876
Original result ↗

LMArena

1,419.581

source id
lmarena
leaderboard name
LMArena Text Style Control Korean
dimension
style
metric
Arena rating
rank
62
sample size
1314
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1402.4383113582785
confidence upper
1436.7233196055258
Original result ↗

LMArena

1,497.392

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Software And It Services
dimension
style
metric
Arena rating
rank
63
sample size
30110
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1493.1547968902307
confidence upper
1501.6293950282725
Original result ↗

LMArena

1,477.529

source id
lmarena
leaderboard name
LMArena Text Style Control French
dimension
style
metric
Arena rating
rank
65
sample size
1985
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1463.0060502653243
confidence upper
1492.051035170374
Original result ↗

LMArena

1,458.694

source id
lmarena
leaderboard name
LMArena Text French
dimension
general
metric
Arena rating
rank
65
sample size
1985
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1444.2157661613996
confidence upper
1473.173038408092
Original result ↗

LMArena

1,462.48

source id
lmarena
leaderboard name
LMArena Text Factuality English
dimension
factuality
metric
Arena rating
rank
66
sample size
30759
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1458.6890058985578
confidence upper
1466.2704017015385
Original result ↗

LMArena

1,446.615

source id
lmarena
leaderboard name
LMArena Text Factuality Industry Mathematical
dimension
factuality
metric
Arena rating
rank
67
sample size
2640
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1436.119183038114
confidence upper
1457.1099744679705
Original result ↗

LMArena

1,454.146

source id
lmarena
leaderboard name
LMArena Text Style Control Russian
dimension
style
metric
Arena rating
rank
69
sample size
9537
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1447.6752681801715
confidence upper
1460.6163601272629
Original result ↗

LMArena

1,449.758

source id
lmarena
leaderboard name
LMArena Text Industry Legal And Government
dimension
general
metric
Arena rating
rank
69
sample size
5934
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1441.7637585491796
confidence upper
1457.7516611310737
Original result ↗

LMArena

1,400.783

source id
lmarena
leaderboard name
LMArena Text Korean
dimension
general
metric
Arena rating
rank
69
sample size
1314
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1383.7485359374953
confidence upper
1417.8169981053793
Original result ↗

LMArena

1,483.734

source id
lmarena
leaderboard name
LMArena Text Style Control Expert
dimension
style
metric
Arena rating
rank
70
sample size
6090
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1475.8464411052491
confidence upper
1491.6213893938063
Original result ↗

LMArena

1,466.621

source id
lmarena
leaderboard name
LMArena Text Style Control English
dimension
style
metric
Arena rating
rank
70
sample size
35463
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1462.666836256631
confidence upper
1470.5743912853632
Original result ↗

LMArena

1,463.841

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Legal And Government
dimension
style
metric
Arena rating
rank
70
sample size
5934
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1455.7856930496228
confidence upper
1471.8959190532728
Original result ↗

LMArena

1,436.97

source id
lmarena
leaderboard name
LMArena Text Russian
dimension
general
metric
Arena rating
rank
70
sample size
9537
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1430.520078641894
confidence upper
1443.4202766034277
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