anthropic

Claude Opus 5

claude-opus

Strongest Claude Opus model for coding, agents, and professional work

ReasoningTool CallingAttachments

Context Window

1M

Max Output

128K

Temperature

No

Open Weights

No

Knowledge Cutoff

2026-05

Released

2026-07-24

Last Updated

2026-07-24

Modalities

Input:TextImagePDF
→
Output:Text

Benchmarks

BenchmarkScoreMetricHarness
SWE-Bench Verified96resolved-
SWE-Bench Pro79.2resolve rate-
SWE-Bench Multilingual89.5resolve rate-
SWE-Bench Multimodal59.4resolve rate-
DeepSWE68.8resolve rate-
FrontierCode53.4mean@5-
Frontier-Bench43.3mean rewardmini-SWE-agent
BrowseComp90.8accuracy-
Humanity's Last Exam56.3accuracy-
Humanity's Last Exam64.7accuracy-
DeepSearchQA95F1-
OSWorld70.6success rate-
GDPval-AA1861Elo-
AA-Briefcase1720Elo-
AutomationBench26success rate-
ARC-AGI-197.5accuracy-
ARC-AGI-290.4accuracy-
ARC-AGI-330.2RHAE-
HealthBench Professional59.8score-

Available Providers (12)

ProviderInput /1MOutput /1MCache Read /1MCache Write /1MReasoningStatus
NanoGPTNanoGPTRp 89.401Rp 447.001Rp 8.941Rp 111.751effort—
LLM GatewayLLM GatewayRp 89.401Rp 447.001Rp 8.941Rp 111.751effort—
Kilo GatewayKilo GatewayRp 89.401Rp 447.001Rp 8.941Rp 111.751effort—
OpenRouterOpenRouterRp 89.401Rp 447.001Rp 8.941Rp 111.751toggle, effort—
Cloudflare AI GatewayCloudflare AI GatewayRp 89.401Rp 447.001Rp 8.941Rp 111.751effort—
Vercel AI GatewayVercel AI GatewayRp 89.401Rp 447.001Rp 8.941Rp 111.751effort, budget_tokens—
OrcaRouterOrcaRouterRp 89.401Rp 447.001Rp 8.941Rp 178.801effort—
OfoxOfoxRp 89.401Rp 447.001Rp 8.941Rp 111.751effort—
Merge GatewayMerge GatewayRp 89.401Rp 447.001Rp 8.941Rp 111.751toggle, effort—
Eden AIEden AIRp 89.401Rp 447.001Rp 8.941Rp 111.751effort—
Tempr GatewayTempr GatewayRp 89.401Rp 447.001Rp 8.941Rp 111.751effort—
CrossModelCrossModelRp 89.401Rp 447.001Rp 8.941Rp 111.751toggle, effort—