Anthropic model product
Claude Sonnet 3
Claude 3 Sonnet strikes the ideal balance between intelligence and speed—particularly for enterprise workloads.
Updated Aug 17, 2026. Default version: Claude 3 Sonnet
LLMBoard Score3.1Claude 3 Sonnet
Coverage80%11 benchmark families
Context window200KTokens
Official input priceN/AOfficial price unavailable
Claude Sonnet 3 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Claude Sonnet 3 Benchmark Results
Benchmark scores for Claude 3 Sonnet.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkHellaSwag | Score89.0% | Rank05 | Participants27 | Percentile84.6% | EvidenceC | Evaluated |
| BenchmarkARC-C | Score93.2% | Rank06 | Participants34 | Percentile84.8% | EvidenceC | Evaluated |
| BenchmarkBIG-Bench Hard | Score82.9% | Rank08 | Participants21 | Percentile65.0% | EvidenceC | Evaluated |
| BenchmarkDROP | Score78.9% | Rank17 | Participants30 | Percentile44.8% | EvidenceC | Evaluated |
| BenchmarkMGSM | Score83.5% | Rank17 | Participants31 | Percentile46.7% | EvidenceC | Evaluated |
| BenchmarkGSM8k | Score92.3% | Rank19 | Participants48 | Percentile61.7% | EvidenceC | Evaluated |
| BenchmarkHumanEval | Score73.0% | Rank53 | Participants66 | Percentile20.0% | EvidenceC | Evaluated |
| BenchmarkMATH | Score43.1% | Rank63 | Participants71 | Percentile11.4% | EvidenceC | Evaluated |
| BenchmarkMMLU | Score79.0% | Rank67 | Participants101 | Percentile34.0% | EvidenceC | Evaluated |
| BenchmarkMMLU-Pro | Score56.8% | Rank110 | Participants134 | Percentile18.1% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score40.4% | Rank209 | Participants239 | Percentile12.6% | EvidenceC | Evaluated |
Claude Sonnet 3 Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenavision | Categoryoverall | Rank132 | Rating / score984.0 | Votes12,314 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank132 | Rating / score1017.1 | Votes12,314 | ObservationsN/A | Result date |
| Arenatext style control | Categoryoverall | Rank275 | Rating / score1280.9 | Votes109,284 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank284 | Rating / score1218.2 | Votes109,284 | ObservationsN/A | Result date |
Claude Sonnet 3 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- N/A
- Tracked offerings
- 0
No provider prices
The default version has no current input or output token prices.
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Claude Sonnet 3 Runtime Performance
Provider-specific output speed and catalog latency for Claude 3 Sonnet. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderBedrock | Output Speed120 tok/s | Catalog Latency0.5 s | Max Input200K | Max Output200K | Updated |
| ProviderAnthropic | Output Speed100 tok/s | Catalog Latency0.5 s | Max Input200K | Max Output200K | Updated |
| ProviderGoogle | Output Speed42 tok/s | Catalog Latency0.4 s | Max Input200K | Max Output200K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Claude Sonnet 3 Specifications
Technical details for the model's default version.
- Version
- Claude 3 Sonnet
- Released
- Feb 29, 2024
- Knowledge cutoff
- Unknown
- Parameters
- N/A
- Context window
- 200K
- Max output
- 200K
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Claude Sonnet 3 Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionClaude 3 Sonnet | Released | LLMBoard3.1 | ParametersN/A | Context200K | Max output200K | Open weightsNo | LicenseProprietary |
Claude Sonnet 3 vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Claude Sonnet 3
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AN
Claude Haiku 3
Anthropic
AN
Claude Haiku 3.5
Anthropic
AN
Claude Opus 3
Anthropic
AN
Claude Sonnet 3.5
Anthropic
AN
Claude Sonnet 3.7
Anthropic
AN
Claude Sonnet 4
Anthropic
What is Claude Sonnet 3?
Key information about Claude Sonnet 3 and its available data.
Claude 3 Sonnet strikes the ideal balance between intelligence and speed—particularly for enterprise workloads. It delivers strong performance at a lower cost compared to its peers, and is engineered for high endurance in large-scale AI deployments.
Data as of 2026-08-17.
FAQ
Common questions about Claude Sonnet 3.
When was Claude Sonnet 3 released?
Claude Sonnet 3's default version was released on Feb 29, 2024.
How much does Claude Sonnet 3 cost?
No official standard PAYG price is currently available for Claude Sonnet 3.
Who created Claude Sonnet 3?
Claude Sonnet 3 was created by Anthropic.
What is the context window for Claude Sonnet 3?
The default version has a 200K token context window.
Is Claude Sonnet 3 open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Claude Sonnet 3?
No provider offering is currently linked to the default version.
What models should I compare Claude Sonnet 3 with?
Nearby ranked alternatives include Nova Micro, GPT-4, GPT-4.1-nano.