Anthropic model product
Claude Opus 4.5
5 is an Anthropic LLM with extended thinking, a 200K context window, 64K maximum output, and an effort parameter for controlling reasoning depth.
Updated Sep 8, 2026. Default version: Claude Opus 4.5
LLMBoard Score68.2Claude Opus 4.5
Coverage20%11 benchmark families
Context window200KTokens
Official input price$5Anthropic API
Claude Opus 4.5 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Claude Opus 4.5 Benchmark Results
Benchmark scores for Claude Opus 4.5.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkMMMU (validation) | Score80.70% | Rank01 | Participants4 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkTau2 Retail | Score88.90% | Rank03 | Participants27 | Percentile92.31% | EvidenceC | Evaluated |
| BenchmarkTau2 Telecom | Score98.20% | Rank05 | Participants36 | Percentile88.57% | EvidenceC | Evaluated |
| BenchmarkOSWorld | Score66.30% | Rank06 | Participants20 | Percentile73.68% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Verified | Score80.90% | Rank06 | Participants113 | Percentile95.54% | EvidenceC | Evaluated |
| BenchmarkMMMLU | Score90.80% | Rank07 | Participants49 | Percentile87.50% | EvidenceC | Evaluated |
| BenchmarkARC-AGI v2 | Score37.60% | Rank12 | Participants18 | Percentile35.29% | EvidenceC | Evaluated |
| BenchmarkLiveBench | Score75.96% | Rank12 | Participants38 | Percentile70.27% | EvidenceB | Evaluated |
| BenchmarkLM Arena Document | Score1,461.65 rating | Rank15 | Participants33 | Percentile56.25% | EvidenceA | Evaluated |
| BenchmarkLM Arena Document Style Control | Score1,464.26 rating | Rank15 | Participants33 | Percentile56.25% | EvidenceA | Evaluated |
| BenchmarkLM Arena Search | Score1,179.64 rating | Rank17 | Participants28 | Percentile40.74% | EvidenceA | Evaluated |
| BenchmarkLM Arena Search Factuality | Score1,180.00 rating | Rank17 | Participants28 | Percentile40.74% | EvidenceA | Evaluated |
| BenchmarkLM Arena Search Style Control | Score1,187.22 rating | Rank17 | Participants28 | Percentile40.74% | EvidenceA | Evaluated |
| BenchmarkTerminal-Bench 2.0 | Score59.30% | Rank21 | Participants51 | Percentile60.00% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,472.84 rating | Rank27 | Participants210 | Percentile87.56% | EvidenceA | Evaluated |
| BenchmarkMCP Atlas | Score62.30% | Rank28 | Participants34 | Percentile18.18% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text Factuality | Score1,458.56 rating | Rank31 | Participants121 | Percentile75.00% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,450.38 rating | Rank35 | Participants210 | Percentile83.73% | EvidenceA | Evaluated |
| BenchmarkLM Arena Webdev | Score1,494.65 rating | Rank38 | Participants97 | Percentile61.46% | EvidenceA | Evaluated |
| BenchmarkGPQA | Score87.00% | Rank49 | Participants247 | Percentile80.49% | EvidenceC | Evaluated |
Claude Opus 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 | Categorycoding | Rank07 | Rating / score1,533.92 | Votes4,626 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryinstruction following | Rank10 | Rating / score1,482.61 | Votes6,440 | ObservationsN/A | Result date |
| Arenatext style control | Categorycoding | Rank11 | Rating / score1,530.48 | Votes7,521 | ObservationsN/A | Result date |
| Arenatext style control | Categoryinstruction following | Rank11 | Rating / score1,483.49 | Votes9,469 | ObservationsN/A | Result date |
| Arenatext | Categorycoding | Rank12 | Rating / score1,503.33 | Votes7,521 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryfrench | Rank12 | Rating / score1,499.16 | Votes569 | ObservationsN/A | Result date |
| Arenatext style control | Categorycreative writing | Rank12 | Rating / score1,468.57 | Votes5,461 | ObservationsN/A | Result date |
| Arenatext | Categoryinstruction following | Rank13 | Rating / score1,477.49 | Votes9,469 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank14 | Rating / score1,446.80 | Votes1,134 | ObservationsN/A | Result date |
| Arenatext style control | Categorylonger query | Rank14 | Rating / score1,493.80 | Votes9,316 | ObservationsN/A | Result date |
| Arenadocument | Categoryoverall | Rank15 | Rating / score1,461.65 | Votes7,965 | ObservationsN/A | Result date |
| Arenadocument style control | Categoryoverall | Rank15 | Rating / score1,464.26 | Votes7,965 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryexpert | Rank15 | Rating / score1,506.44 | Votes3,539 | ObservationsN/A | Result date |
| Arenatext style control | Categorygerman | Rank16 | Rating / score1,477.37 | Votes656 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry entertainment and sports and media | Rank16 | Rating / score1,456.15 | Votes6,684 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank16 | Rating / score1,473.57 | Votes1,117 | ObservationsN/A | Result date |
| Arenasearch | Categoryoverall | Rank17 | Rating / score1,179.64 | Votes61,573 | ObservationsN/A | Result date |
| Arenasearch factuality | Categoryoverall | Rank17 | Rating / score1,180.00 | Votes61,402 | ObservationsN/A | Result date |
| Arenasearch style control | Categoryoverall | Rank17 | Rating / score1,187.22 | Votes61,573 | ObservationsN/A | Result date |
| Arenatext factuality | Categorygerman | Rank17 | Rating / score1,421.03 | Votes589 | ObservationsN/A | Result date |
| Arenatext factuality | Categorylonger query | Rank17 | Rating / score1,490.83 | Votes18,246 | ObservationsN/A | Result date |
| Arenatext | Categoryhard prompts english | Rank18 | Rating / score1,481.61 | Votes18,085 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryhard prompts english | Rank18 | Rating / score1,502.95 | Votes13,646 | ObservationsN/A | Result date |
| Arenatext factuality | Categorykorean | Rank18 | Rating / score1,411.53 | Votes591 | ObservationsN/A | Result date |
| Arenatext style control | Categoryhard prompts english | Rank18 | Rating / score1,503.69 | Votes7,610 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry legal and government | Rank18 | Rating / score1,486.53 | Votes2,638 | ObservationsN/A | Result date |
| Arenatext | Categorylonger query | Rank19 | Rating / score1,479.46 | Votes22,818 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry mathematical | Rank19 | Rating / score1,472.01 | Votes2,396 | ObservationsN/A | Result date |
| Arenatext factuality | Categorymulti turn | Rank19 | Rating / score1,478.53 | Votes8,642 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry software and it services | Rank19 | Rating / score1,511.48 | Votes12,217 | ObservationsN/A | Result date |
Claude Opus 4.5 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $5 input, $25 output per 1M
- Official provider
- Anthropic
- Lowest third-party
- From $0.71 input, $3.57 output per 1M via QiHang
- Tracked offerings
- 37
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderQiHang | Provider model IDclaude-opus-4-5-20251101 | Regionglobal | Input / 1M$0.71 | Output / 1M$3.57 | Context200K | Updated |
| ProviderPoe | Provider model IDanthropic/claude-opus-4.5 | Regionglobal | Input / 1M$4.3 | Output / 1M$21 | Context196.6K | Updated |
| ProviderJiekou.AI | Provider model IDclaude-opus-4-5-20251101 | Regionglobal | Input / 1M$4.5 | Output / 1M$22.5 | Context200K | Updated |
| ProviderOrcaRouter | Provider model IDanthropic/claude-opus-4.5 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context200K | Updated |
| ProviderNanoGPT | Provider model IDclaude-opus-4-5-20251101 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context200K | Updated |
| ProviderVertex | Provider model IDclaude-opus-4-5@20251101 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context200K | Updated |
| ProviderImpossibl | Provider model IDanthropic/claude-opus-4-5 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context200K | Updated |
| ProviderOpenRouter | Provider model IDanthropic/claude-opus-4.5 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context200K | Updated |
| ProviderVertex (Anthropic) | Provider model IDclaude-opus-4-5@20251101 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context200K | Updated |
| ProviderAnthropic | Provider model IDclaude-opus-4-5 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context200K | Updated |
| ProviderAnthropic | Provider model IDclaude-opus-4-5-20251101 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context200K | Updated |
| ProviderDatabricks | Provider model IDdatabricks-claude-opus-4-5 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context200K | Updated |
| ProviderAmazon Bedrock | Provider model IDanthropic.claude-opus-4-5-20251101-v1:0 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context200K | Updated |
| ProviderOpper | Provider model IDanthropic/claude-opus-4-5 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context200K | Updated |
| ProviderLLM Gateway | Provider model IDanthropic/claude-opus-4-5-20251101 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context200K | Updated |
| ProviderMerge Gateway | Provider model IDanthropic/claude-opus-4-5-20251101 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context200K | Updated |
| ProviderCloudflare AI Gateway | Provider model IDanthropic/claude-opus-4.5 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context200K | Updated |
| ProviderZenMux | Provider model IDanthropic/claude-opus-4.5 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context200K | Updated |
| ProviderPerplexity Agent | Provider model IDanthropic/claude-opus-4-5 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context200K | Updated |
| ProviderOfox | Provider model IDanthropic/claude-opus-4.5 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context200K | Updated |
| ProviderNeon | Provider model IDclaude-opus-4-5 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context200K | Updated |
| ProviderAzure Cognitive Services | Provider model IDclaude-opus-4-5 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context200K | Updated |
| Provider302.AI | Provider model IDclaude-opus-4-5 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context200K | Updated |
| Provider302.AI | Provider model IDclaude-opus-4-5-20251101 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context200K | Updated |
| ProviderOpenCode Zen | Provider model IDclaude-opus-4-5 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context200K | Updated |
| ProviderRequesty | Provider model IDclaude-opus-4-5 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context200K | Updated |
| ProviderAzure | Provider model IDclaude-opus-4-5 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context200K | Updated |
| ProviderVercel AI Gateway | Provider model IDanthropic/claude-opus-4.5 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context200K | Updated |
| ProviderEden AI | Provider model IDanthropic/claude-opus-4-5 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context200K | Updated |
| ProviderEden AI | Provider model IDanthropic/claude-opus-4-5-20251101 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context200K | Updated |
Claude Opus 4.5 Runtime Performance
Provider-specific output speed and catalog latency for Claude Opus 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 Latency0.50 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 Opus 4.5 Specifications
Technical details for the model's default version.
- Version
- Claude Opus 4.5
- Released
- Nov 24, 2025
- Knowledge cutoff
- Mar 31, 2025
- Parameters
- N/A
- Context window
- 200K
- Max output
- 64K
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Claude Opus 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 Opus 4.5 | Released | LLMBoard68.22 | ParametersN/A | Context200K | Max output64K | Open weightsNo | LicenseProprietary |
Models similar to Claude Opus 4.5
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AN
Claude Sonnet 4.6
Anthropic
AN
Claude Opus 4.6
Anthropic
AN
Claude Sonnet 5
Anthropic
AN
Claude Sonnet 4.5
Anthropic
AN
Claude Opus 4.7
Anthropic
AN
Claude Opus 4.1
Anthropic
What is Claude Opus 4.5?
Key information about Claude Opus 4.5 and its available data.
5 is a large language model from Anthropic designed for coding, agents, and computer use. It supports a 200K context window, 64K maximum output, extended thinking, an effort parameter for controlling reasoning depth, and pricing of $5/$25 per million tokens for input/output.
Data as of 2026-09-08.
FAQ
Common questions about Claude Opus 4.5.
When was Claude Opus 4.5 released?
Claude Opus 4.5's default version was released on Nov 24, 2025.
How much does Claude Opus 4.5 cost?
Claude Opus 4.5's official API price is $5 per million input tokens and $25 per million output tokens via Anthropic. The lowest tracked third-party offer starts at $0.71 input and $3.57 output via QiHang.
Who created Claude Opus 4.5?
Claude Opus 4.5 was created by Anthropic.
What is the context window for Claude Opus 4.5?
The default version has a 200K token context window.
Is Claude Opus 4.5 open weight?
No. The default version is not marked as having publicly available weights.