Anthropic model product
Claude Opus 4.8
7, with reported improvements in software engineering, agentic tool use, reasoning, computer use, and knowledge work.
Updated Oct 23, 2026. Default version: Claude Opus 4.8
LLMBoard Score83.1Claude Opus 4.8
Coverage80%27 benchmark families
Context window1MTokens
Official input price$5Anthropic API
Claude Opus 4.8 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Claude Opus 4.8 Benchmark Results
Benchmark scores for Claude Opus 4.8.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkInclude | Score87.60% | Rank01 | Participants31 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkLM Arena Agent Bash Reliability No Prereq | Score15.74% | Rank01 | Participants45 | Percentile100.00% | EvidenceA | Evaluated |
| BenchmarkGraphwalks parents >128k | Score83.30% | Rank02 | Participants7 | Percentile83.33% | EvidenceC | Evaluated |
| BenchmarkScreenSpot Pro | Score87.90% | Rank02 | Participants26 | Percentile96.00% | EvidenceC | Evaluated |
| BenchmarkDeepSearchQA | Score93.10% | Rank03 | Participants13 | Percentile83.33% | EvidenceC | Evaluated |
| BenchmarkOfficeQA Pro | Score66.20% | Rank04 | Participants12 | Percentile72.73% | EvidenceC | Evaluated |
| BenchmarkOSWorld-Verified | Score83.40% | Rank04 | Participants28 | Percentile88.89% | EvidenceC | Evaluated |
| BenchmarkSWE-bench Multilingual | Score84.40% | Rank04 | Participants50 | Percentile93.88% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Verified | Score88.60% | Rank04 | Participants120 | Percentile97.48% | EvidenceC | Evaluated |
| BenchmarkFrontierSWE | Score75.00% | Rank05 | Participants17 | Percentile75.00% | EvidenceB | Evaluated |
| BenchmarkSWE-Bench Multimodal | Score38.40% | Rank05 | Participants7 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Pro | Score69.20% | Rank05 | Participants63 | Percentile93.55% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score93.60% | Rank06 | Participants256 | Percentile98.04% | EvidenceC | Evaluated |
| BenchmarkGraphwalks BFS >128k | Score68.10% | Rank06 | Participants12 | Percentile54.55% | EvidenceC | Evaluated |
| BenchmarkLiveBench | Score77.22% | Rank06 | Participants38 | Percentile86.49% | EvidenceB | Evaluated |
| BenchmarkCharXiv-R | Score89.90% | Rank07 | Participants60 | Percentile89.83% | EvidenceC | Evaluated |
| BenchmarkFinance Agent | Score53.90% | Rank07 | Participants8 | Percentile14.29% | EvidenceC | Evaluated |
| BenchmarkFinance Agent v2 | Score53.92% | Rank07 | Participants29 | Percentile78.57% | EvidenceB | Evaluated |
| BenchmarkMCP Atlas | Score82.20% | Rank07 | Participants39 | Percentile84.21% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 2.0 | Score74.60% | Rank07 | Participants53 | Percentile88.46% | EvidenceC | Evaluated |
| BenchmarkLM Arena Agent Bash Recovery Steps | Score7.22% | Rank07 | Participants44 | Percentile86.05% | EvidenceA | Evaluated |
| BenchmarkLM Arena Document Style Control | Score1,485.93 rating | Rank07 | Participants38 | Percentile83.78% | EvidenceA | Evaluated |
| BenchmarkAA HLE Text No Tools | Score48.66% | Rank07 | Participants200 | Percentile96.98% | EvidenceB | EvaluatedN/A |
| BenchmarkFrontierCode 1.1 | Score46.50% | Rank09 | Participants23 | Percentile63.64% | EvidenceB | Evaluated |
| BenchmarkHumanity's Last Exam | Score57.90% | Rank09 | Participants109 | Percentile92.59% | EvidenceC | Evaluated |
| BenchmarkLM Arena Document | Score1,474.79 rating | Rank09 | Participants38 | Percentile78.38% | EvidenceA | Evaluated |
| BenchmarkToolathlon | Score59.90% | Rank11 | Participants42 | Percentile75.61% | EvidenceC | Evaluated |
| BenchmarkAA CritPt | Score20.86% | Rank11 | Participants200 | Percentile94.97% | EvidenceB | EvaluatedN/A |
| BenchmarkBrowseComp | Score84.30% | Rank15 | Participants70 | Percentile79.71% | EvidenceC | Evaluated |
| BenchmarkCyberGym | Score78.80% | Rank15 | Participants23 | Percentile36.36% | EvidenceC | Evaluated |
Claude Opus 4.8 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 no prereq | Categoryoverall | Rank01 | Rating / score0.16 | VotesN/A | Observations12.2K | Result date |
| Arenaagent bash recovery steps | Categoryoverall | Rank07 | Rating / score0.07 | VotesN/A | Observations40.7K | Result date |
| Arenadocument style control | Categoryoverall | Rank07 | Rating / score1,485.93 | Votes11,551 | ObservationsN/A | Result date |
| Arenatext style control | Categoryhard prompts english | Rank08 | Rating / score1,516.75 | Votes18,802 | ObservationsN/A | Result date |
| Arenavision | Categoryhomework | Rank08 | Rating / score1,336.81 | Votes2,077 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhomework | Rank08 | Rating / score1,331.83 | Votes2,077 | ObservationsN/A | Result date |
| Arenadocument | Categoryoverall | Rank09 | Rating / score1,474.79 | Votes11,551 | ObservationsN/A | Result date |
| Arenatext style control | Categoryinstruction following | Rank09 | Rating / score1,490.80 | Votes22,656 | ObservationsN/A | Result date |
| Arenatext style control | Categorymulti turn | Rank09 | Rating / score1,496.87 | Votes11,184 | ObservationsN/A | Result date |
| Arenatext factuality | Categorygerman | Rank10 | Rating / score1,443.84 | Votes522 | ObservationsN/A | Result date |
| Arenatext style control | Categorylonger query | Rank10 | Rating / score1,502.74 | Votes30,196 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry mathematical | Rank11 | Rating / score1,485.17 | Votes2,985 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryjapanese | Rank11 | Rating / score1,456.31 | Votes546 | ObservationsN/A | Result date |
| Arenatext factuality | Categorypolish | Rank11 | Rating / score1,460.43 | Votes600 | ObservationsN/A | Result date |
| Arenatext style control | Categoryhard prompts | Rank11 | Rating / score1,512.86 | Votes42,516 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry business and management and financial operations | Rank11 | Rating / score1,488.83 | Votes12,740 | ObservationsN/A | Result date |
| Arenavision style control | Categorycreative writing vision | Rank11 | Rating / score1,289.09 | Votes1,398 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry mathematical | Rank12 | Rating / score1,506.75 | Votes3,478 | ObservationsN/A | Result date |
| Arenavision style control | Categoryenglish | Rank12 | Rating / score1,281.43 | Votes7,311 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry mathematical | Rank13 | Rating / score1,497.12 | Votes3,478 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryfrench | Rank13 | Rating / score1,503.25 | Votes1,803 | ObservationsN/A | Result date |
| Arenatext factuality | Categorymulti turn | Rank13 | Rating / score1,490.45 | Votes10,125 | ObservationsN/A | Result date |
| Arenatext style control | Categoryfrench | Rank13 | Rating / score1,507.18 | Votes2,188 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry software and it services | Rank13 | Rating / score1,523.11 | Votes25,111 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank13 | Rating / score1,480.58 | Votes1,860 | ObservationsN/A | Result date |
| Arenatext factuality | Categorykorean | Rank14 | Rating / score1,433.48 | Votes602 | ObservationsN/A | Result date |
| Arenatext style control | Categorycoding | Rank14 | Rating / score1,533.22 | Votes17,413 | ObservationsN/A | Result date |
| Arenatext style control | Categorycreative writing | Rank14 | Rating / score1,468.96 | Votes12,792 | ObservationsN/A | Result date |
| Arenatext style control | Categoryexpert | Rank14 | Rating / score1,525.97 | Votes7,057 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry legal and government | Rank14 | Rating / score1,497.62 | Votes5,523 | ObservationsN/A | Result date |
Claude Opus 4.8 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 $0.425 input, $2.13 output per 1M via UnoRouter
- Tracked offerings
- 49
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderUnoRouter | Provider model IDclaude-opus-4-8 | Regionglobal | Input / 1M$0.425 | Output / 1M$2.13 | Context1M | Updated |
| ProviderXpersona | Provider model IDclaude-opus-4-8 | Regionglobal | Input / 1M$1.5 | Output / 1M$9.25 | Context200K | Updated |
| ProviderPoe | Provider model IDanthropic/claude-opus-4.8 | Regionglobal | Input / 1M$4.29 | Output / 1M$21.46 | Context1M | Updated |
| ProviderOrcaRouter | Provider model IDanthropic/claude-opus-4.8 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context1M | Updated |
| ProviderNanoGPT | Provider model IDanthropic/claude-opus-4.8 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context1M | Updated |
| ProviderVertex | Provider model IDclaude-opus-4-8@default | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context1M | Updated |
| ProviderImpossibl | Provider model IDanthropic/claude-opus-4-8 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context1M | Updated |
| ProviderOpenRouter | Provider model IDanthropic/claude-opus-4.8 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context1M | Updated |
| ProviderVertex (Anthropic) | Provider model IDclaude-opus-4-8@default | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context1M | Updated |
| ProviderDaoXE | Provider model IDclaude-opus-4-8 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context1M | Updated |
| ProviderCrossModel | Provider model IDanthropic/claude-opus-4-8 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context1M | Updated |
| ProviderSnowflake Cortex | Provider model IDclaude-opus-4-8 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context1M | Updated |
| ProviderAnthropic | Provider model IDclaude-opus-4-8 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context1M | Updated |
| Providerrouting.run | Provider model IDclaude-opus-4-8 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context1M | Updated |
| ProviderAmazon Bedrock | Provider model IDanthropic.claude-opus-4-8 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context1M | Updated |
| ProviderLLM Gateway | Provider model IDanthropic/claude-opus-4-8 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context1M | Updated |
| ProviderMerge Gateway | Provider model IDanthropic/claude-opus-4-8 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context1M | Updated |
| ProviderCloudflare AI Gateway | Provider model IDanthropic/claude-opus-4.8 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context1M | Updated |
| ProviderFastRouter | Provider model IDanthropic/claude-opus-4.8 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context1M | Updated |
| ProviderZenMux | Provider model IDanthropic/claude-opus-4.8 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context1M | Updated |
| ProviderGMI Cloud | Provider model IDanthropic/claude-opus-4.8 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context1M | Updated |
| ProviderFreeModel | Provider model IDclaude-opus-4-8 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context1M | Updated |
| ProviderOfox | Provider model IDanthropic/claude-opus-4.8 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context1M | Updated |
| ProviderNeon | Provider model IDclaude-opus-4-8 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context1M | Updated |
| ProviderAzure Cognitive Services | Provider model IDclaude-opus-4-8 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context1M | Updated |
| ProviderOpenCode | Provider model IDclaude-opus-4-8 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context1M | Updated |
| ProviderRequesty | Provider model IDclaude-opus-4-8 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context1M | Updated |
| ProviderAzure | Provider model IDclaude-opus-4-8 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context1M | Updated |
| ProviderAIHubMix | Provider model IDclaude-opus-4-8 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context1M | Updated |
| ProviderAIHubMix | Provider model IDclaude-opus-4-8-think | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context1M | Updated |
Claude Opus 4.8 Runtime Performance
Provider-specific output speed and catalog latency for Claude Opus 4.8. 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 Input1M | Max Output128K | Updated |
| ProviderVertex AI | Output Speed42.00 tok/s | Catalog Latency0.50 s | Max Input1M | Max Output128K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Claude Opus 4.8 Specifications
Technical details for the model's default version.
- Version
- Claude Opus 4.8
- Released
- May 28, 2026
- Knowledge cutoff
- Unknown
- Parameters
- N/A
- Context window
- 1M
- Max output
- 1M
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Claude Opus 4.8 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 4.8 | Released | LLMBoard83.07 | ParametersN/A | Context1M | Max output1M | Open weightsNo | LicenseProprietary |
Models similar to Claude Opus 4.8
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AN
Claude Opus 4.7
Anthropic
AN
Claude Haiku 5.5
Anthropic
AN
Claude Sonnet 5
Anthropic
AN
Claude Opus 4.6
Anthropic
AN
Claude Fable 5
Anthropic
AN
Claude Mythos
Anthropic
What is Claude Opus 4.8?
Key information about Claude Opus 4.8 and its available data.
7. At release, Anthropic described it as its most capable general-access model, with high, extra (xhigh), and max effort levels for different task demands.
Data as of 2026-10-22.
FAQ
Common questions about Claude Opus 4.8.
When was Claude Opus 4.8 released?
Claude Opus 4.8's default version was released on May 28, 2026.
How much does Claude Opus 4.8 cost?
Claude Opus 4.8'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 $0.425 input and $2.13 output via UnoRouter.
Who created Claude Opus 4.8?
Claude Opus 4.8 was created by Anthropic.
What is the context window for Claude Opus 4.8?
The default version has a 1M token context window.
Is Claude Opus 4.8 open weight?
No. The default version is not marked as having publicly available weights.