Anthropic model product
Claude Sonnet 5
Claude Sonnet 5 is Anthropic's Sonnet-class LLM for reasoning, tool use, coding, computer use, and knowledge work.
Updated Oct 23, 2026. Default version: Claude Sonnet 5
LLMBoard Score77.8Claude Sonnet 5
Coverage60%22 benchmark families
Context window1MTokens
Official input price$2Anthropic API
Claude Sonnet 5 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Claude Sonnet 5 Benchmark Results
Benchmark scores for Claude Sonnet 5.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkChartMuseum | Score86.70% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkGDP.pdf | Score81.60% | Rank01 | Participants14 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkLM Arena Agent Bash Reliability | Score15.48% | Rank01 | Participants44 | Percentile100.00% | EvidenceA | Evaluated |
| BenchmarkUSAMO 2026 | Score33.39 points | Rank02 | Participants3 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkLM Arena Agent Bash Reliability No Prereq | Score15.57% | Rank02 | Participants45 | Percentile97.73% | EvidenceA | Evaluated |
| BenchmarkArXivMath | Score72.20% | Rank03 | Participants5 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 2.0 | Score80.40% | Rank03 | Participants53 | Percentile96.15% | EvidenceC | Evaluated |
| BenchmarkFrontierCode | Score38.80% | Rank04 | Participants4 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkLegal Agent Benchmark | Score5.80% | Rank06 | Participants15 | Percentile64.29% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Verified | Score85.20% | Rank06 | Participants120 | Percentile95.80% | EvidenceC | Evaluated |
| BenchmarkLM Arena Agent Bash Recovery Steps | Score7.38% | Rank06 | Participants44 | Percentile88.37% | EvidenceA | Evaluated |
| BenchmarkBenchCAD | Score37.30% | Rank07 | Participants7 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkOSWorld-Verified | Score81.20% | Rank07 | Participants28 | Percentile77.78% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Multimodal | Score28.10% | Rank07 | Participants7 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkLM Arena Agent Leaderboard | Score4.15% | Rank07 | Participants44 | Percentile86.05% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Steerability | Score6.12% | Rank08 | Participants44 | Percentile83.72% | EvidenceA | Evaluated |
| BenchmarkHumanity's Last Exam | Score57.40% | Rank10 | Participants109 | Percentile91.67% | EvidenceC | Evaluated |
| BenchmarkOfficeQA Pro | Score59.40% | Rank10 | Participants12 | Percentile18.18% | EvidenceC | Evaluated |
| BenchmarkSWE-bench Multilingual | Score78.30% | Rank10 | Participants50 | Percentile81.63% | EvidenceC | Evaluated |
| BenchmarkCharXiv-R | Score88.30% | Rank12 | Participants60 | Percentile81.36% | EvidenceC | Evaluated |
| BenchmarkLM Arena Document Style Control | Score1,475.70 rating | Rank12 | Participants38 | Percentile70.27% | EvidenceA | Evaluated |
| BenchmarkBrowseComp | Score84.70% | Rank13 | Participants70 | Percentile82.61% | EvidenceC | Evaluated |
| BenchmarkFrontierCode 1.1 | Score42.70% | Rank13 | Participants23 | Percentile45.45% | EvidenceB | Evaluated |
| BenchmarkLM Arena Agent Praise Complaint | Score4.36% | Rank13 | Participants44 | Percentile72.09% | EvidenceA | Evaluated |
| BenchmarkHealthBench Professional | Score57.80% | Rank14 | Participants20 | Percentile31.58% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Pro | Score63.20% | Rank14 | Participants63 | Percentile79.03% | EvidenceC | Evaluated |
| BenchmarkLM Arena Document | Score1,466.14 rating | Rank14 | Participants38 | Percentile64.86% | EvidenceA | Evaluated |
| BenchmarkAA LCR v1.1 | Score82.00% | Rank16 | Participants193 | Percentile92.19% | EvidenceB | EvaluatedN/A |
| BenchmarkToolathlon | Score54.30% | Rank17 | Participants42 | Percentile60.98% | EvidenceC | Evaluated |
| BenchmarkLM Arena Search Style Control | Score1,193.16 rating | Rank19 | Participants33 | Percentile43.75% | EvidenceA | Evaluated |
Claude Sonnet 5 Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenaagent bash reliability | Categoryoverall | Rank01 | Rating / score0.15 | VotesN/A | Observations74.4K | Result date |
| Arenaagent bash reliability no prereq | Categoryoverall | Rank02 | Rating / score0.16 | VotesN/A | Observations44.5K | Result date |
| Arenaagent bash recovery steps | Categoryoverall | Rank06 | Rating / score0.07 | VotesN/A | Observations125.2K | Result date |
| Arenaagent | Categoryoverall | Rank07 | Rating / score0.04 | VotesN/A | Observations3.7M | Result date |
| Arenaagent steerability | Categoryoverall | Rank08 | Rating / score0.06 | VotesN/A | Observations47.1K | Result date |
| Arenatext factuality | Categorygerman | Rank11 | Rating / score1,443.30 | Votes368 | ObservationsN/A | Result date |
| Arenadocument style control | Categoryoverall | Rank12 | Rating / score1,475.70 | Votes7,411 | ObservationsN/A | Result date |
| Arenaagent praise complaint | Categoryoverall | Rank13 | Rating / score0.04 | VotesN/A | Observations7.6K | Result date |
| Arenadocument | Categoryoverall | Rank14 | Rating / score1,466.14 | Votes7,411 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry mathematical | Rank16 | Rating / score1,480.95 | Votes2,329 | ObservationsN/A | Result date |
| Arenatext factuality | Categorykorean | Rank16 | Rating / score1,425.08 | Votes446 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryjapanese | Rank17 | Rating / score1,440.26 | Votes425 | ObservationsN/A | Result date |
| Arenasearch style control | Categoryoverall | Rank19 | Rating / score1,193.16 | Votes72,978 | ObservationsN/A | Result date |
| Arenaagent tool hallucination | Categoryoverall | Rank20 | Rating / score0.00 | VotesN/A | Observations3.5M | Result date |
| Arenasearch factuality | Categoryoverall | Rank20 | Rating / score1,181.75 | Votes72,978 | ObservationsN/A | Result date |
| Arenaagent task outcome explicit | Categoryoverall | Rank21 | Rating / score0.00 | VotesN/A | Observations22.4K | Result date |
| Arenasearch | Categoryoverall | Rank21 | Rating / score1,190.94 | Votes72,978 | ObservationsN/A | Result date |
| Arenatext style control | Categoryexpert | Rank21 | Rating / score1,510.36 | Votes5,651 | ObservationsN/A | Result date |
| Arenavision | Categoryhomework | Rank23 | Rating / score1,311.05 | Votes1,500 | ObservationsN/A | Result date |
| Arenavision style control | Categorychinese | Rank23 | Rating / score1,316.21 | Votes847 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhomework | Rank23 | Rating / score1,304.57 | Votes1,500 | ObservationsN/A | Result date |
| Arenawebdev | Categoryimage to webdev | Rank23 | Rating / score1,539.86 | Votes8,124 | ObservationsN/A | Result date |
| Arenatext factuality | Categorymath | Rank25 | Rating / score1,473.32 | Votes1,953 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryfrench | Rank26 | Rating / score1,487.79 | Votes1,364 | ObservationsN/A | Result date |
| Arenavision | Categorychinese | Rank26 | Rating / score1,330.65 | Votes847 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryexpert | Rank27 | Rating / score1,502.60 | Votes4,982 | ObservationsN/A | Result date |
| Arenatext style control | Categorycoding | Rank28 | Rating / score1,519.29 | Votes13,564 | ObservationsN/A | Result date |
| Arenavision | Categorydiagram | Rank29 | Rating / score1,292.59 | Votes3,718 | ObservationsN/A | Result date |
| Arenatext | Categoryexpert | Rank30 | Rating / score1,489.24 | Votes5,651 | ObservationsN/A | Result date |
| Arenavision | Categoryocr | Rank30 | Rating / score1,287.62 | Votes9,827 | ObservationsN/A | Result date |
Claude Sonnet 5 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $2 input, $10 output per 1M
- Official provider
- Anthropic
- Lowest third-party
- From $1.43 input, $7.14 output per 1M via Kenari
- Tracked offerings
- 43
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderKenari | Provider model IDclaude-sonnet-5 | Regionglobal | Input / 1M$1.43 | Output / 1M$7.14 | Context1M | Updated |
| ProviderUnoRouter | Provider model IDclaude-sonnet-5 | Regionglobal | Input / 1M$1.44 | Output / 1M$7.2 | Context1M | Updated |
| ProviderOrcaRouter | Provider model IDanthropic/claude-sonnet-5 | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderNanoGPT | Provider model IDanthropic/claude-sonnet-5 | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderVertex | Provider model IDclaude-sonnet-5@default | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderImpossibl | Provider model IDanthropic/claude-sonnet-5 | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderOpenRouter | Provider model IDanthropic/claude-sonnet-5 | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderVertex (Anthropic) | Provider model IDclaude-sonnet-5@default | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderCrossModel | Provider model IDanthropic/claude-sonnet-5 | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderSnowflake Cortex | Provider model IDclaude-sonnet-5 | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderAnthropic | Provider model IDclaude-sonnet-5 | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderAmazon Bedrock | Provider model IDanthropic.claude-sonnet-5 | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderLLM Gateway | Provider model IDanthropic/claude-sonnet-5 | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderMerge Gateway | Provider model IDanthropic/claude-sonnet-5 | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderCloudflare AI Gateway | Provider model IDanthropic/claude-sonnet-5 | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderZenMux | Provider model IDanthropic/claude-sonnet-5 | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderOfox | Provider model IDanthropic/claude-sonnet-5 | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderNeon | Provider model IDclaude-sonnet-5 | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderAzure Cognitive Services | Provider model IDclaude-sonnet-5 | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderOpenCode | Provider model IDclaude-sonnet-5 | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderRequesty | Provider model IDclaude-sonnet-5 | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderAzure | Provider model IDclaude-sonnet-5 | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderAIHubMix | Provider model IDclaude-sonnet-5 | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderVercel AI Gateway | Provider model IDanthropic/claude-sonnet-5 | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderEden AI | Provider model IDanthropic/claude-sonnet-5 | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDclaude-sonnet-5 | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderGitHub Copilot | Provider model IDclaude-sonnet-5 | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderKilo Gateway | Provider model IDanthropic/claude-sonnet-5 | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderPioneer | Provider model IDclaude-sonnet-5 | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
| ProviderVenice AI | Provider model IDclaude-sonnet-5 | Regionglobal | Input / 1M$2 | Output / 1M$10 | Context1M | Updated |
Claude Sonnet 5 Runtime Performance
Provider-specific output speed and catalog latency for Claude Sonnet 5. 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 Input1M | Max Output64K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Claude Sonnet 5 Specifications
Technical details for the model's default version.
- Version
- Claude Sonnet 5
- Released
- Jun 30, 2026
- Knowledge cutoff
- Unknown
- Parameters
- N/A
- Context window
- 1M
- Max output
- 1M
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Claude Sonnet 5 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 Sonnet 5 | Released | LLMBoard77.80 | ParametersN/A | Context1M | Max output1M | Open weightsNo | LicenseProprietary |
Models similar to Claude Sonnet 5
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AN
Claude Opus 4.6
Anthropic
AN
Claude Haiku 5.5
Anthropic
AN
Claude Opus 4.7
Anthropic
AN
Claude Mythos 5.1
Anthropic
AN
Claude Opus 4.8
Anthropic
AN
Claude Sonnet 4.6
Anthropic
What is Claude Sonnet 5?
Key information about Claude Sonnet 5 and its available data.
6 that can plan, use tools such as browsers and terminals, and run autonomously for long-horizon tasks. It supports adaptive thinking with effort levels up to extra high (xhigh) and a 1M-token context window with context compaction.
Data as of 2026-10-22.
FAQ
Common questions about Claude Sonnet 5.
When was Claude Sonnet 5 released?
Claude Sonnet 5's default version was released on Jun 30, 2026.
How much does Claude Sonnet 5 cost?
Claude Sonnet 5's official API price is $2 per million input tokens and $10 per million output tokens via Anthropic. The lowest tracked third-party offer starts at $1.43 input and $7.14 output via Kenari.
Who created Claude Sonnet 5?
Claude Sonnet 5 was created by Anthropic.
What is the context window for Claude Sonnet 5?
The default version has a 1M token context window.
Is Claude Sonnet 5 open weight?
No. The default version is not marked as having publicly available weights.