Anthropic model product
Claude Sonnet 3.7
7 is an Anthropic large language model with hybrid reasoning and strengths in coding and front-end web development.
Updated Oct 23, 2026. Default version: Claude 3.7 Sonnet
LLMBoard Score36.5Claude 3.7 Sonnet
Coverage80%11 benchmark families
Context window200KTokens
Official input priceN/AOfficial price unavailable
Claude Sonnet 3.7 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Claude Sonnet 3.7 Benchmark Results
Benchmark scores for Claude 3.7 Sonnet.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkTAU-bench Retail | Score81.20% | Rank04 | Participants25 | Percentile87.50% | EvidenceC | Evaluated |
| BenchmarkIFEval | Score93.20% | Rank08 | Participants70 | Percentile89.86% | EvidenceC | Evaluated |
| BenchmarkTAU-bench Airline | Score58.40% | Rank09 | Participants23 | Percentile63.64% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench | Score35.20% | Rank14 | Participants25 | Percentile45.83% | EvidenceC | Evaluated |
| BenchmarkMATH-500 | Score96.20% | Rank15 | Participants33 | Percentile56.25% | EvidenceC | Evaluated |
| BenchmarkMMMLU | Score86.10% | Rank25 | Participants51 | Percentile52.00% | EvidenceC | Evaluated |
| BenchmarkMMMU | Score75.00% | Rank25 | Participants66 | Percentile63.08% | EvidenceC | Evaluated |
| BenchmarkAIME 2024 | Score80.00% | Rank28 | Participants54 | Percentile49.06% | EvidenceC | Evaluated |
| BenchmarkAA AIME 2025 | Score56.33% | Rank53 | Participants96 | Percentile45.26% | EvidenceB | EvaluatedN/A |
| BenchmarkAA Omniscience Accuracy | Score28.20% | Rank67 | Participants201 | Percentile67.00% | EvidenceB | EvaluatedN/A |
| BenchmarkSWE-Bench Verified | Score70.30% | Rank69 | Participants120 | Percentile42.86% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score84.80% | Rank70 | Participants256 | Percentile72.94% | EvidenceC | Evaluated |
| BenchmarkLM Arena Vision Style Control | Score1,192.66 rating | Rank79 | Participants113 | Percentile30.36% | EvidenceA | Evaluated |
| BenchmarkLM Arena Vision | Score1,168.88 rating | Rank83 | Participants113 | Percentile26.79% | EvidenceA | Evaluated |
| BenchmarkAA IFBench | Score48.30% | Rank93 | Participants168 | Percentile44.91% | EvidenceB | EvaluatedN/A |
| BenchmarkAA CritPt | Score0.86% | Rank95 | Participants200 | Percentile52.76% | EvidenceB | EvaluatedN/A |
| BenchmarkAIME 2025 | Score54.80% | Rank106 | Participants122 | Percentile13.22% | EvidenceC | Evaluated |
| BenchmarkAA GPQA Diamond | Score77.17% | Rank113 | Participants199 | Percentile43.43% | EvidenceB | EvaluatedN/A |
| BenchmarkAA LCR v1.1 | Score51.67% | Rank126 | Participants193 | Percentile34.90% | EvidenceB | EvaluatedN/A |
| BenchmarkAA HLE Text No Tools | Score9.67% | Rank130 | Participants200 | Percentile35.18% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Text Style Control | Score1,388.38 rating | Rank131 | Participants218 | Percentile40.09% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,314.37 rating | Rank166 | Participants218 | Percentile23.96% | EvidenceA | Evaluated |
Claude Sonnet 3.7 Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenavision style control | Categoryhomework | Rank72 | Rating / score1,228.10 | Votes217 | ObservationsN/A | Result date |
| Arenavision style control | Categorychinese | Rank73 | Rating / score1,198.96 | Votes163 | ObservationsN/A | Result date |
| Arenavision style control | Categorydiagram | Rank76 | Rating / score1,214.67 | Votes301 | ObservationsN/A | Result date |
| Arenavision style control | Categoryocr | Rank76 | Rating / score1,209.76 | Votes863 | ObservationsN/A | Result date |
| Arenavision | Categorychinese | Rank77 | Rating / score1,174.02 | Votes163 | ObservationsN/A | Result date |
| Arenavision | Categoryhomework | Rank77 | Rating / score1,206.28 | Votes217 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank79 | Rating / score1,192.66 | Votes1,436 | ObservationsN/A | Result date |
| Arenavision | Categorydiagram | Rank82 | Rating / score1,175.96 | Votes301 | ObservationsN/A | Result date |
| Arenavision | Categoryocr | Rank82 | Rating / score1,180.70 | Votes863 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank83 | Rating / score1,168.88 | Votes1,436 | ObservationsN/A | Result date |
| Arenavision style control | Categoryenglish | Rank84 | Rating / score1,185.80 | Votes644 | ObservationsN/A | Result date |
| Arenavision | Categoryenglish | Rank87 | Rating / score1,164.33 | Votes644 | ObservationsN/A | Result date |
| Arenatext style control | Categorycreative writing | Rank91 | Rating / score1,392.93 | Votes5,146 | ObservationsN/A | Result date |
| Arenatext style control | Categoryinstruction following | Rank96 | Rating / score1,411.36 | Votes10,120 | ObservationsN/A | Result date |
| Arenatext style control | Categorylonger query | Rank96 | Rating / score1,429.62 | Votes6,134 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry entertainment and sports and media | Rank101 | Rating / score1,385.64 | Votes6,542 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry writing and literature and language | Rank102 | Rating / score1,393.88 | Votes8,763 | ObservationsN/A | Result date |
| Arenatext style control | Categoryjapanese | Rank106 | Rating / score1,342.93 | Votes1,018 | ObservationsN/A | Result date |
| Arenatext style control | Categorygerman | Rank110 | Rating / score1,386.30 | Votes1,022 | ObservationsN/A | Result date |
| Arenatext style control | Categorypolish | Rank111 | Rating / score1,376.07 | Votes2,193 | ObservationsN/A | Result date |
| Arenatext style control | Categorycoding | Rank116 | Rating / score1,452.15 | Votes6,134 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank117 | Rating / score1,332.45 | Votes767 | ObservationsN/A | Result date |
| Arenatext style control | Categoryhard prompts | Rank119 | Rating / score1,418.45 | Votes13,721 | ObservationsN/A | Result date |
| Arenatext style control | Categoryhard prompts english | Rank119 | Rating / score1,427.53 | Votes6,983 | ObservationsN/A | Result date |
| Arenatext style control | Categorymulti turn | Rank119 | Rating / score1,400.09 | Votes6,142 | ObservationsN/A | Result date |
| Arenatext style control | Categoryexpert | Rank124 | Rating / score1,411.40 | Votes1,889 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry medicine and healthcare | Rank124 | Rating / score1,408.96 | Votes2,240 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry legal and government | Rank126 | Rating / score1,396.65 | Votes2,474 | ObservationsN/A | Result date |
| Arenatext style control | Categoryrussian | Rank127 | Rating / score1,377.63 | Votes3,354 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank127 | Rating / score1,377.38 | Votes612 | ObservationsN/A | Result date |
Claude Sonnet 3.7 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- From $3 input, $15 output per 1M via Merge Gateway
- Tracked offerings
- 5
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderMerge Gateway | Provider model IDanthropic/claude-3-7-sonnet-20250219 | Regionglobal | Input / 1M$3 | Output / 1M$15 | Context200K | Updated |
| ProviderDigitalOcean | Provider model IDanthropic-claude-3.7-sonnet | Regionglobal | Input / 1M$3 | Output / 1M$15 | Context200K | Updated |
| ProviderZenMux | Provider model IDanthropic/claude-3.7-sonnet | Regionglobal | Input / 1M$3 | Output / 1M$15 | Context200K | Updated |
| ProviderAbacus | Provider model IDclaude-3-7-sonnet-20250219 | Regionglobal | Input / 1M$3 | Output / 1M$15 | Context200K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Claude Sonnet 3.7 Runtime Performance
Provider-specific output speed and catalog latency for Claude 3.7 Sonnet. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderAnthropic | Output Speed42.00 tok/s | Catalog Latency0.40 s | Max Input200K | Max Output128K | Updated |
| ProviderGoogle | Output Speed42.00 tok/s | Catalog Latency0.40 s | Max Input200K | Max Output128K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Claude Sonnet 3.7 Specifications
Technical details for the model's default version.
- Version
- Claude 3.7 Sonnet
- Released
- Feb 24, 2025
- Knowledge cutoff
- Unknown
- Parameters
- N/A
- Context window
- 200K
- Max output
- 128K
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Claude Sonnet 3.7 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 3.7 Sonnet | Released | LLMBoard36.54 | ParametersN/A | Context200K | Max output128K | Open weightsNo | LicenseProprietary |
Models similar to Claude Sonnet 3.7
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AN
Claude Sonnet 4
Anthropic
AN
Claude Sonnet 3.5
Anthropic
AN
Claude Haiku 4.5
Anthropic
AN
Claude Opus 4
Anthropic
AN
Claude Opus 4.1
Anthropic
AN
Claude Sonnet 4.5
Anthropic
What is Claude Sonnet 3.7?
Key information about Claude Sonnet 3.7 and its available data.
7 is a hybrid reasoning large language model from Anthropic that can provide near-instant responses or extended, visible step-by-step thinking. It includes improvements in coding and front-end web development.
Data as of 2026-10-22.
FAQ
Common questions about Claude Sonnet 3.7.
When was Claude Sonnet 3.7 released?
Claude Sonnet 3.7's default version was released on Feb 24, 2025.
How much does Claude Sonnet 3.7 cost?
No official standard PAYG price is currently available for Claude Sonnet 3.7. The lowest tracked third-party offer starts at $3 input and $15 output via Merge Gateway.
Who created Claude Sonnet 3.7?
Claude Sonnet 3.7 was created by Anthropic.
What is the context window for Claude Sonnet 3.7?
The default version has a 200K token context window.
Is Claude Sonnet 3.7 open weight?
No. The default version is not marked as having publicly available weights.