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
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 ↗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 ↗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 ↗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 ↗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 ↗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 ↗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
- source model id
- anthropic.claude-sonnet-4-20250514-v1:0
- hosting
- bedrock-managed
Safety assessments
1–1 / 1
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
Explore more models