Anthropic model product
Claude Sonnet 4.5
5 is an LLM from Anthropic with coding, agent-building, computer-use, reasoning, and math capabilities.
Updated Oct 23, 2026. Default version: Claude Sonnet 4.5
LLMBoard Score54.9Claude Sonnet 4.5
Coverage60%8 benchmark families
Context window200KTokens
Official input price$3Anthropic API
Claude Sonnet 4.5 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Claude Sonnet 4.5 Benchmark Results
Benchmark scores for Claude Sonnet 4.5.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkSWE-bench Verified (Agentic Coding) | Score77.20% | Rank01 | Participants2 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkTAU-bench Airline | Score70.00% | Rank01 | Participants23 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkTAU-bench Retail | Score86.20% | Rank01 | Participants25 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench | Score50.00% | Rank01 | Participants25 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMMMUval | Score77.80% | Rank03 | Participants4 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkOSWorld | Score61.40% | Rank09 | Participants21 | Percentile60.00% | EvidenceC | Evaluated |
| BenchmarkMMMLU | Score89.10% | Rank13 | Participants51 | Percentile76.00% | EvidenceC | Evaluated |
| BenchmarkLM Arena Document | Score1,449.81 rating | Rank23 | Participants38 | Percentile40.54% | EvidenceA | Evaluated |
| BenchmarkLM Arena Search Factuality | Score1,162.49 rating | Rank24 | Participants33 | Percentile28.13% | EvidenceA | Evaluated |
| BenchmarkLM Arena Search | Score1,160.27 rating | Rank25 | Participants33 | Percentile25.00% | EvidenceA | Evaluated |
| BenchmarkLM Arena Search Style Control | Score1,175.98 rating | Rank25 | Participants33 | Percentile25.00% | EvidenceA | Evaluated |
| BenchmarkAA AIME 2025 | Score88.00% | Rank26 | Participants96 | Percentile73.68% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Document Style Control | Score1,449.08 rating | Rank28 | Participants38 | Percentile27.03% | EvidenceA | Evaluated |
| BenchmarkAA SciCode Subtasks | Score45.72% | Rank44 | Participants89 | Percentile51.14% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Text Style Control | Score1,456.38 rating | Rank46 | Participants218 | Percentile79.26% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Factuality | Score1,448.58 rating | Rank52 | Participants131 | Percentile60.77% | EvidenceA | Evaluated |
| BenchmarkAA Omniscience Accuracy | Score32.87% | Rank53 | Participants201 | Percentile74.00% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Text | Score1,438.49 rating | Rank58 | Participants218 | Percentile73.73% | EvidenceA | Evaluated |
| BenchmarkAIME 2025 | Score87.00% | Rank59 | Participants122 | Percentile52.07% | EvidenceC | Evaluated |
| BenchmarkLM Arena Webdev | Score1,393.73 rating | Rank74 | Participants107 | Percentile31.13% | EvidenceA | Evaluated |
| BenchmarkAA IFBench | Score57.28% | Rank79 | Participants168 | Percentile53.29% | EvidenceB | EvaluatedN/A |
| BenchmarkAA LCR v1.1 | Score72.33% | Rank79 | Participants193 | Percentile59.38% | EvidenceB | EvaluatedN/A |
| BenchmarkGPQA | Score83.40% | Rank81 | Participants256 | Percentile68.63% | EvidenceC | Evaluated |
| BenchmarkAA GPQA Diamond | Score83.43% | Rank83 | Participants199 | Percentile58.59% | EvidenceB | EvaluatedN/A |
| BenchmarkAA CritPt | Score1.14% | Rank91 | Participants200 | Percentile54.77% | EvidenceB | EvaluatedN/A |
| BenchmarkAA HLE Text No Tools | Score17.79% | Rank97 | Participants200 | Percentile51.76% | EvidenceB | EvaluatedN/A |
Claude Sonnet 4.5 Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext factuality | Categorylonger query | Rank22 | Rating / score1,487.41 | Votes18,415 | ObservationsN/A | Result date |
| Arenadocument | Categoryoverall | Rank23 | Rating / score1,449.81 | Votes31,455 | ObservationsN/A | Result date |
| Arenasearch factuality | Categoryoverall | Rank24 | Rating / score1,162.49 | Votes143,960 | ObservationsN/A | Result date |
| Arenatext factuality | Categorykorean | Rank24 | Rating / score1,412.93 | Votes620 | ObservationsN/A | Result date |
| Arenasearch | Categoryoverall | Rank25 | Rating / score1,160.27 | Votes144,153 | ObservationsN/A | Result date |
| Arenasearch style control | Categoryoverall | Rank25 | Rating / score1,175.98 | Votes144,153 | ObservationsN/A | Result date |
| Arenatext style control | Categorycreative writing | Rank25 | Rating / score1,453.98 | Votes12,425 | ObservationsN/A | Result date |
| Arenatext factuality | Categorycoding | Rank26 | Rating / score1,521.63 | Votes13,451 | ObservationsN/A | Result date |
| Arenatext | Categorylonger query | Rank27 | Rating / score1,475.44 | Votes26,471 | ObservationsN/A | Result date |
| Arenadocument style control | Categoryoverall | Rank28 | Rating / score1,449.08 | Votes31,455 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryspanish | Rank28 | Rating / score1,457.90 | Votes1,434 | ObservationsN/A | Result date |
| Arenatext style control | Categorylonger query | Rank28 | Rating / score1,485.59 | Votes26,077 | ObservationsN/A | Result date |
| Arenatext factuality | Categorygerman | Rank29 | Rating / score1,404.73 | Votes648 | ObservationsN/A | Result date |
| Arenatext style control | Categorycoding | Rank29 | Rating / score1,518.84 | Votes19,940 | ObservationsN/A | Result date |
| Arenatext | Categoryinstruction following | Rank30 | Rating / score1,459.07 | Votes24,365 | ObservationsN/A | Result date |
| Arenatext factuality | Categorycreative writing | Rank30 | Rating / score1,446.52 | Votes7,611 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryinstruction following | Rank30 | Rating / score1,468.49 | Votes17,083 | ObservationsN/A | Result date |
| Arenatext | Categorycreative writing | Rank31 | Rating / score1,441.77 | Votes12,425 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryhard prompts english | Rank31 | Rating / score1,498.10 | Votes13,804 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank31 | Rating / score1,466.36 | Votes2,500 | ObservationsN/A | Result date |
| Arenatext | Categorycoding | Rank32 | Rating / score1,488.22 | Votes19,940 | ObservationsN/A | Result date |
| Arenatext style control | Categoryhard prompts english | Rank32 | Rating / score1,494.53 | Votes21,152 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry entertainment and sports and media | Rank32 | Rating / score1,445.59 | Votes16,160 | ObservationsN/A | Result date |
| Arenatext factuality | Categorymulti turn | Rank33 | Rating / score1,472.43 | Votes9,077 | ObservationsN/A | Result date |
| Arenatext style control | Categorymulti turn | Rank33 | Rating / score1,477.50 | Votes14,467 | ObservationsN/A | Result date |
| Arenatext | Categorymulti turn | Rank34 | Rating / score1,464.88 | Votes14,467 | ObservationsN/A | Result date |
| Arenatext | Categoryspanish | Rank34 | Rating / score1,457.60 | Votes2,500 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry entertainment and sports and media | Rank34 | Rating / score1,439.96 | Votes10,225 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry writing and literature and language | Rank34 | Rating / score1,450.98 | Votes12,350 | ObservationsN/A | Result date |
| Arenatext | Categoryexpert | Rank35 | Rating / score1,482.60 | Votes6,086 | ObservationsN/A | Result date |
Claude Sonnet 4.5 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $3 input, $15 output per 1M
- Official provider
- Anthropic
- Lowest third-party
- From $0.43 input, $2.14 output per 1M via QiHang
- Tracked offerings
- 42
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderQiHang | Provider model IDclaude-sonnet-4-5-20250929 | Regionglobal | Input / 1M$0.43 | Output / 1M$2.14 | Context200K | Updated |
| ProviderPoe | Provider model IDanthropic/claude-sonnet-4.5 | Regionglobal | Input / 1M$2.58 | Output / 1M$12.88 | Context983K | Updated |
| ProviderCortecs | Provider model IDclaude-4-5-sonnet | Regionglobal | Input / 1M$2.99 | Output / 1M$14.95 | Context200K | Updated |
| ProviderOrcaRouter | Provider model IDanthropic/claude-sonnet-4.5 | Regionglobal | Input / 1M$3 | Output / 1M$15 | Context1M | Updated |
| ProviderVertex | Provider model IDclaude-sonnet-4-5@20250929 | Regionglobal | Input / 1M$3 | Output / 1M$15 | Context200K | Updated |
| ProviderImpossibl | Provider model IDanthropic/claude-sonnet-4-5 | Regionglobal | Input / 1M$3 | Output / 1M$15 | Context200K | Updated |
| ProviderJiekou.AI | Provider model IDclaude-sonnet-4-5-20250929 | Regionglobal | Input / 1M$3 | Output / 1M$15 | Context200K | Updated |
| ProviderOpenRouter | Provider model IDanthropic/claude-sonnet-4.5 | Regionglobal | Input / 1M$3 | Output / 1M$15 | Context1M | Updated |
| ProviderVertex (Anthropic) | Provider model IDclaude-sonnet-4-5@20250929 | Regionglobal | Input / 1M$3 | Output / 1M$15 | Context200K | Updated |
| ProviderSnowflake Cortex | Provider model IDclaude-sonnet-4-5 | Regionglobal | Input / 1M$3 | Output / 1M$15 | Context200K | Updated |
| ProviderAnthropic | Provider model IDclaude-sonnet-4-5-20250929 | Regionglobal | Input / 1M$3 | Output / 1M$15 | Context200K | Updated |
| ProviderAnthropic | Provider model IDclaude-sonnet-4-5 | Regionglobal | Input / 1M$3 | Output / 1M$15 | Context200K | Updated |
| ProviderDatabricks | Provider model IDdatabricks-claude-sonnet-4-5 | Regionglobal | Input / 1M$3 | Output / 1M$15 | Context200K | Updated |
| ProviderAmazon Bedrock | Provider model IDanthropic.claude-sonnet-4-5-20250929-v1:0 | Regionglobal | Input / 1M$3 | Output / 1M$15 | Context200K | Updated |
| ProviderLLM Gateway | Provider model IDanthropic/claude-sonnet-4-5-20250929 | Regionglobal | Input / 1M$3 | Output / 1M$15 | Context200K | Updated |
| ProviderLLM Gateway | Provider model IDanthropic/claude-sonnet-4-5 | Regionglobal | Input / 1M$3 | Output / 1M$15 | Context200K | Updated |
| ProviderNEAR AI Cloud | Provider model IDanthropic/claude-sonnet-4-5 | Regionglobal | Input / 1M$3 | Output / 1M$15 | Context200K | Updated |
| ProviderMerge Gateway | Provider model IDanthropic/claude-sonnet-4-5-20250929 | Regionglobal | Input / 1M$3 | Output / 1M$15 | Context200K | Updated |
| ProviderCloudflare AI Gateway | Provider model IDanthropic/claude-sonnet-4.5 | Regionglobal | Input / 1M$3 | Output / 1M$15 | Context200K | Updated |
| ProviderZenMux | Provider model IDanthropic/claude-sonnet-4.5 | Regionglobal | Input / 1M$3 | Output / 1M$15 | Context1M | Updated |
| ProviderPerplexity Agent | Provider model IDanthropic/claude-sonnet-4-5 | Regionglobal | Input / 1M$3 | Output / 1M$15 | Context200K | Updated |
| ProviderOfox | Provider model IDanthropic/claude-sonnet-4.5 | Regionglobal | Input / 1M$3 | Output / 1M$15 | Context200K | Updated |
| ProviderHelicone | Provider model IDclaude-sonnet-4-5-20250929 | Regionglobal | Input / 1M$3 | Output / 1M$15 | Context200K | Updated |
| ProviderNeon | Provider model IDclaude-sonnet-4-5 | Regionglobal | Input / 1M$3 | Output / 1M$15 | Context200K | Updated |
| ProviderAzure Cognitive Services | Provider model IDclaude-sonnet-4-5 | Regionglobal | Input / 1M$3 | Output / 1M$15 | Context200K | Updated |
| Provider302.AI | Provider model IDclaude-sonnet-4-5-20250929 | Regionglobal | Input / 1M$3 | Output / 1M$15 | Context200K | Updated |
| ProviderOpenCode | Provider model IDclaude-sonnet-4-5 | Regionglobal | Input / 1M$3 | Output / 1M$15 | Context1M | Updated |
| ProviderRequesty | Provider model IDclaude-sonnet-4-5 | Regionglobal | Input / 1M$3 | Output / 1M$15 | Context1M | Updated |
| ProviderAzure | Provider model IDclaude-sonnet-4-5 | Regionglobal | Input / 1M$3 | Output / 1M$15 | Context200K | Updated |
| ProviderVercel AI Gateway | Provider model IDanthropic/claude-sonnet-4.5 | Regionglobal | Input / 1M$3 | Output / 1M$15 | Context200K | Updated |
Claude Sonnet 4.5 Runtime Performance
Provider-specific output speed and catalog latency for Claude Sonnet 4.5. 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 Input200K | Max Output64K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Claude Sonnet 4.5 Specifications
Technical details for the model's default version.
- Version
- Claude Sonnet 4.5
- Released
- Sep 29, 2025
- Knowledge cutoff
- Jan 31, 2025
- Parameters
- N/A
- Context window
- 200K
- Max output
- 64K
- Inputs
- audio, image, text, video
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Claude Sonnet 4.5 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 4.5 | Released | LLMBoard54.92 | ParametersN/A | Context200K | Max output64K | Open weightsNo | LicenseProprietary |
Models similar to Claude Sonnet 4.5
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AN
Claude Opus 4.1
Anthropic
AN
Claude Opus 4
Anthropic
AN
Claude Haiku 4.5
Anthropic
AN
Claude Opus 4.5
Anthropic
AN
Claude Sonnet 4.6
Anthropic
AN
Claude Sonnet 4
Anthropic
What is Claude Sonnet 4.5?
Key information about Claude Sonnet 4.5 and its available data.
5 is a large language model from Anthropic. The source describes it as supporting coding, complex agents, computer use, reasoning, and math tasks.
Data as of 2026-10-22.
FAQ
Common questions about Claude Sonnet 4.5.
When was Claude Sonnet 4.5 released?
Claude Sonnet 4.5's default version was released on Sep 29, 2025.
How much does Claude Sonnet 4.5 cost?
Claude Sonnet 4.5's official API price is $3 per million input tokens and $15 per million output tokens via Anthropic. The lowest tracked third-party offer starts at $0.43 input and $2.14 output via QiHang.
Who created Claude Sonnet 4.5?
Claude Sonnet 4.5 was created by Anthropic.
What is the context window for Claude Sonnet 4.5?
The default version has a 200K token context window.
Is Claude Sonnet 4.5 open weight?
No. The default version is not marked as having publicly available weights.