Claude Opus 4.6 by Anthropic demonstrates top-tier general intelligence, excellent coding ability, outstanding mathematical reasoning. View detailed benchmark data including scores across coding, math, reasoning, speed, and cost metrics.
Specifications last checked against the provider on . Benchmark scores carry their own source, linked beside each number.
General Benchmarks
Massive Multitask Language Understanding professional benchmark
HuggingFace LeaderboardCoding Benchmarks
Human preference ELO for building a working web page from a brief
Design Arena (via OpenRouter)Human preference ELO for building things — websites, UI, games, charts, SVG
Design Arena (via OpenRouter)Math Benchmarks
Reasoning Benchmarks
Multi-turn service agent making tool calls under strict policy constraints
OpenRouter (measured)Speed Benchmarks
Cost Benchmarks
Cost per 1M cached input tokens — the price that actually applies to a long agent conversation
OpenRouter APIContext Benchmarks
Available from 37 providers
The same model costs different amounts depending on who serves it. You can bring your own key for 6 of these — connect it here.
| Provider | Input / 1M | Output / 1M | Cached in | Context | Your key |
|---|---|---|---|---|---|
| Poe | $4.3 | $21 | $0.43 | 983K | — |
| Abacus | $5 | $25 | — | 1.0M | — |
| AIHubMix | $5 | $25 | $0.5 | 1.0M | — |
| Amazon Bedrock | $5 | $25 | $0.5 | 1.0M | Supported |
| Anthropic | $5 | $25 | $0.5 | 1.0M | Supported |
| Auriko | $5 | $25 | $0.5 | 1.0M | — |
| Azure | $5 | $25 | $0.5 | 1.0M | Supported |
| Azure Cognitive Services | $5 | $25 | $0.5 | 1.0M | — |
| Cloudflare AI Gateway | $5 | $25 | $0.5 | 1.0M | — |
| Databricks | $5 | $25 | $0.5 | 1.0M | — |
| DevPass (LLM Gateway) | $5 | $25 | $0.5 | 1.0M | — |
| Eden AI | $5 | $25 | $0.5 | 1.0M | — |
| FreeModel | $5 | $25 | $0.5 | 1.0M | — |
| FrogBot | $5 | $25 | $0.5 | 200K | — |
| GMI Cloud | $5 | $25 | $0.5 | 410K | — |
| Impossibl | $5 | $25 | $0.5 | 1.0M | — |
| Kilo Gateway | $5 | $25 | $0.5 | 1.0M | — |
| LLM Gateway | $5 | $25 | $0.5 | 1.0M | — |
| Merge Gateway | $5 | $25 | $0.5 | 1.0M | — |
| NEAR AI Cloud | $5 | $25 | $0.5 | 200K | — |
| Neon | $5 | $25 | $0.5 | 1.0M | — |
| Ofox | $5 | $25 | $0.5 | 1.0M | — |
| OpenCode Zen | $5 | $25 | $0.5 | 1.0M | — |
| OpenRouter | $5 | $25 | $0.5 | 1.0M | Supported |
| Opper | $5 | $25 | $0.5 | 1.0M | — |
| OrcaRouter | $5 | $25 | $0.5 | 1.0M | — |
| Perplexity Agent | $5 | $25 | $0.5 | 200K | — |
| Pioneer | $5 | $25 | $0.5 | 1.0M | — |
| Requesty | $5 | $25 | $0.5 | 1.0M | — |
| Vercel AI Gateway | $5 | $25 | $0.5 | 1.0M | Supported |
| Vertex | $5 | $25 | $0.5 | 1.0M | Supported |
| Vertex (Anthropic) | $5 | $25 | $0.5 | 1.0M | — |
| ZenMux | $5 | $25 | $0.5 | 1.0M | — |
| Cortecs | $5.313 | $26.561 | $0.531 | 1.0M | — |
| Venice AI | $6 | $30 | $0.6 | 1.0M | — |
| AnyAPI | — | — | — | 1.0M | — |
| Snowflake Cortex | — | — | — | 1.0M | — |
Claude Opus 4.6 — Benchmark Scores Overview
Scores normalized to percentage scale for visual comparison. ELO scores mapped to 0-100 range (1100-1500).
Compare Claude Opus 4.6 With
Claude Opus 4.6 — Frequently Asked Questions
How intelligent is Claude Opus 4.6?
Claude Opus 4.6 scores 1496 on the Chatbot Arena ELO rating, making it one of the top-ranked AI model. This score is based on blind head-to-head human preference voting.
How much does Claude Opus 4.6 cost?
Claude Opus 4.6 costs $5.0 per 1M input tokens and $25.0 per 1M output tokens. This places it in the premium pricing tier.
How fast is Claude Opus 4.6?
Claude Opus 4.6 generates output at 68 tokens per second, which is slower, prioritizing quality over speed compared to other models. The time to first token is 1680 ms.
How good is Claude Opus 4.6 at coding?
Claude Opus 4.6 achieves 80.8% on SWE-bench Verified, demonstrating excellent real-world software engineering capability. This benchmark tests the model's ability to resolve actual GitHub issues.
How good is Claude Opus 4.6 at math and reasoning?
Claude Opus 4.6 scores 92.0% on the MATH benchmark (competition-level mathematics). It also achieves 85.3% on GPQA Diamond, a graduate-level science reasoning benchmark.
What is the context window of Claude Opus 4.6?
Claude Opus 4.6 has a context window of 1.0M tokens. This determines how much text, conversation history, and code the model can process in a single request.
Who created Claude Opus 4.6?
Claude Opus 4.6 was created by Anthropic. It is classified as a flagship model in our catalogue.
Is Claude Opus 4.6 open source?
No, Claude Opus 4.6 is a proprietary model. It is available through Anthropic's API and compatible providers.