Claude Sonnet 4

Explore Claude Sonnet 4: model specifications, capabilities, benchmark results, platform pricing and original sources.

awsBedrock/anthropic.claude-sonnet-4-20250514-v1:0

Specifications & capabilities

Input
text, image
Output
text
Capabilities
multimodal, visionInput

Evaluations

1–7 / 7

SWE-bench

34.43%

source id
sweBench
leaderboard name
SWE-bench Multimodal
dimension
coding
metric
Resolved tasks
rank
4
evaluated at
2025-05-28T00:00:00.000Z
Original result ↗

HELM Capabilities

84.3%

source id
helm
leaderboard name
HELM MMLU-Pro
dimension
intelligence
metric
chain_of_thought_correctness
rank
10
sample size
1000
source model id
anthropic/claude-sonnet-4-20250514
Original result ↗

HELM Capabilities

51.25%

source id
helm
leaderboard name
HELM Omni-MATH
dimension
intelligence
metric
omni_math_accuracy
rank
17
sample size
1000
source model id
anthropic/claude-sonnet-4-20250514
Original result ↗

HELM Capabilities

64.35%

source id
helm
leaderboard name
HELM GPQA
dimension
intelligence
metric
chain_of_thought_correctness
rank
22
sample size
446
source model id
anthropic/claude-sonnet-4-20250514
Original result ↗

HELM Capabilities

82.47%

source id
helm
leaderboard name
HELM WildBench
dimension
agentic
metric
wildbench_score_rescaled
rank
23
sample size
1000
source model id
anthropic/claude-sonnet-4-20250514
Original result ↗

HELM Capabilities

83.888%

source id
helm
leaderboard name
HELM IFEval
dimension
agentic
metric
ifeval_strict_accuracy
rank
27
sample size
541
source model id
anthropic/claude-sonnet-4-20250514
Original result ↗

SWE-bench

57%

source id
sweBench
leaderboard name
SWE-bench Verified
dimension
coding
metric
Resolved tasks
rank
86
evaluated at
2025-09-24T00:00:00.000Z
Original result ↗

Provider specifications & access

1–1 / 1

Claude Sonnet 4 ↗

source model id
anthropic.claude-sonnet-4-20250514-v1:0
hosting
bedrock-managed
platforms
  • Amazon Bedrock
architecture
input_modalities
  • text
  • image
output_modalities
  • text
capabilities

    Safety assessments

    1–1 / 1

    Foundation Model Transparency Index 2025 ↗

    46 / 100

    source id
    stanfordFMTI
    canonical model id
    awsBedrock/anthropic.claude-sonnet-4-20250514-v1:0
    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

    Original sources

    1–6 / 6

    Amazon Web Services · Model page ↗

    Amazon Bedrock · Model documentation ↗

    Amazon Web Services · Catalog ↗

    GitHub · Catalog ↗

    crfm.stanford.edu · Catalog ↗

    www.swebench.com · Catalog ↗

    Source links

    1–4 / 4

    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