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

21–40 / 125

LMArena

1,457.684

source id
lmarena
leaderboard name
LMArena Text Factuality Spanish
dimension
factuality
metric
Arena rating
rank
32
sample size
1454
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1443.171793301677
confidence upper
1472.1969900381494
Original result ↗

OpenRouter Benchmarks

81.619%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Azure
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
32
sample size
2178
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
11
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Azure
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T08:17:29.306Z
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
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
2178
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8161921818181818
accuracy_std_dev
0.005314989759986385
cost_per_task_usd
0.34637480073461896
output_tokens_per_task
22900.560146923784
latency_seconds_per_task
358.9314338842975
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
43
benchmark_evaluation
true
openrouter_permaslug
anthropic/claude-4.5-sonnet-20250929
source model id
anthropic/claude-4.5-sonnet-20250929
Original result ↗

LMArena

1,486.931

source id
lmarena
leaderboard name
LMArena Text Factuality Longer Query
dimension
factuality
metric
Arena rating
rank
34
sample size
19300
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1482.104961321969
confidence upper
1491.7578190544948
Original result ↗

LMArena

1,454.666

source id
lmarena
leaderboard name
LMArena Text Style Control Creative Writing
dimension
style
metric
Arena rating
rank
35
sample size
12300
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1448.6512066159946
confidence upper
1460.6812318028426
Original result ↗

LMArena

1,447.982

source id
lmarena
leaderboard name
LMArena Document Style Control Overall
dimension
productivity
metric
Arena rating
rank
35
sample size
32916
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1441.8266313382885
confidence upper
1454.1370163412062
Original result ↗

LMArena

1,403.759

source id
lmarena
leaderboard name
LMArena Text Factuality German
dimension
factuality
metric
Arena rating
rank
35
sample size
643
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1381.860639184947
confidence upper
1425.657555964024
Original result ↗

LMArena

1,521.98

source id
lmarena
leaderboard name
LMArena Text Factuality Coding
dimension
factuality
metric
Arena rating
rank
38
sample size
13280
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1516.332855469213
confidence upper
1527.627333928783
Original result ↗

LMArena

1,475.581

source id
lmarena
leaderboard name
LMArena Text Longer Query
dimension
general
metric
Arena rating
rank
38
sample size
26231
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1470.9844700880158
confidence upper
1480.176681565406
Original result ↗

LMArena

1,447.327

source id
lmarena
leaderboard name
LMArena Text Factuality Creative Writing
dimension
factuality
metric
Arena rating
rank
39
sample size
7521
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1440.623348174863
confidence upper
1454.0310422228742
Original result ↗

SWE-bench

70.6%

source id
sweBench
leaderboard name
SWE-bench Verified
dimension
coding
metric
Resolved tasks
rank
40
sample size
500
evaluated at
2025-09-29T00:00:00.000Z
Original result ↗

LMArena

1,442.334

source id
lmarena
leaderboard name
LMArena Text Creative Writing
dimension
general
metric
Arena rating
rank
42
sample size
12300
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1436.3331506857644
confidence upper
1448.33530642329
Original result ↗

LMArena

1,481.803

source id
lmarena
leaderboard name
LMArena Text Style Control Longer Query
dimension
style
metric
Arena rating
rank
43
sample size
26231
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1477.1734259587615
confidence upper
1486.4316364293493
Original result ↗

LMArena

1,464.856

source id
lmarena
leaderboard name
LMArena Text Multi Turn
dimension
general
metric
Arena rating
rank
43
sample size
14403
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1459.2442976869079
confidence upper
1470.4671061383578
Original result ↗

LMArena

1,468.651

source id
lmarena
leaderboard name
LMArena Text Factuality Instruction Following
dimension
factuality
metric
Arena rating
rank
44
sample size
16934
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1463.52828863397
confidence upper
1473.774506321709
Original result ↗

LMArena

1,459.261

source id
lmarena
leaderboard name
LMArena Text Instruction Following
dimension
general
metric
Arena rating
rank
44
sample size
24184
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1454.673010857107
confidence upper
1463.8498338255163
Original result ↗

LMArena

1,440.512

source id
lmarena
leaderboard name
LMArena Text Factuality Industry Entertainment And Sports And Media
dimension
factuality
metric
Arena rating
rank
44
sample size
10108
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1434.3291907401012
confidence upper
1446.6944446232126
Original result ↗

LMArena

1,465.605

source id
lmarena
leaderboard name
LMArena Text Style Control Spanish
dimension
style
metric
Arena rating
rank
46
sample size
2483
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1453.1443959740977
confidence upper
1478.0658091947748
Original result ↗

LMArena

1,451.333

source id
lmarena
leaderboard name
LMArena Text Factuality Industry Writing And Literature And Language
dimension
factuality
metric
Arena rating
rank
46
sample size
12254
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1445.7168332594808
confidence upper
1456.9499350764606
Original result ↗

LMArena

1,471.852

source id
lmarena
leaderboard name
LMArena Text Factuality Multi Turn
dimension
factuality
metric
Arena rating
rank
47
sample size
9037
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1465.0357960651113
confidence upper
1478.6681002196788
Original result ↗

LMArena

1,457.164

source id
lmarena
leaderboard name
LMArena Text Spanish
dimension
general
metric
Arena rating
rank
47
sample size
2483
evaluated at
2026-11-09T00:00:00.000Z
source model id
Claude Sonnet 4.5 (20250929)
confidence lower
1444.7653439512692
confidence upper
1469.5626285949527
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