Claude Opus 5の料金と性能、前世代モデルや他モデルとの違い

"Claude Opus 5 is available today on all platforms, priced at $5 per million input tokens and $25 per million output tokens (the same as Opus 4.8)." ／ "Claude Opus 5 is available today. It’s a thoughtful and proactive model that comes close to the frontier intelligence of Claude Fable 5 at half the price." ／ "It’s also offered in Fast mode, where it runs around 2.5 times the default speed. As with Opus 4.8, Fast mode is available at twice Opus 5’s base price on the Claude Platform and through usage credits in Claude Code." — Anthropic 公式ニュースの冒頭と「Getting started」節より

"$10 / input MTok" ／ "$50 / output MTok" — Claude Docs「Latest models comparison」表 Pricing 行の Claude Fable 5 列より

"For example, on Frontier-Bench v0.1, Opus 5 surpasses all other models, and more than doubles Opus 4.8’s performance at a lower cost per task. On CursorBench 3.2, at max effort, the model performs within 0.5% of Fable 5’s peak score, but at half the cost per task" ／ "On ARC-AGI 3, an evaluation where the model has to solve novel problems, Opus 5’s score is three times as high as the next-best model." ／ "On OSWorld 2.0, a computer use benchmark, Opus 5 outperforms every other model at any given cost, surpassing Fable 5’s best result at just over a third of the cost." — Anthropic 公式ニュース「Performance and cost-effectiveness」節より

Artificial Analysis Intelligence Index v4.3.2 incorporates 10 evaluations: AA-Briefcase v1.1, GDPval-AA v2.1, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1 ／ The top AI models by Intelligence Index are: 1. Claude Opus 5.5 (Adaptive Reasoning, Max Effort, Default Fallback) (58), 2. Claude Opus 5.5 (Adaptive Reasoning, Xhigh Effort, Default Fallback) (56), 3. Claude Opus 5.5 (Adaptive Reasoning, High Effort, Default Fallback) (54), 4. Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback) (53), and 5. Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback) (53). — 同ページの Intelligence Index の定義と、下部 FAQ「What are the top AI models?」より

"Claude Opus 5 (Adaptive Reasoning, Max Effort) scores 51 on the Artificial Analysis Intelligence Index, placing it well above average among comparable models (median: 26)." ／ "Claude Opus 5 (Adaptive Reasoning, Max Effort) is amongst the leading models in intelligence, but particularly expensive when comparing to other models of similar price." ／ "On average, it costs $5.86 per task to evaluate Claude Opus 5 (Adaptive Reasoning, Max Effort) on the Intelligence Index." ／ "Intelligence Updated # 11 / 211" ／ "211 models in this class" — モデルページの Model summary と Comparison Summary より

"The charts in this section show how performance changes according to the model’s effort setting, which customers can use to optimize for intelligence or conserve tokens for faster and cheaper results." — Anthropic 公式ニュース「Performance and cost-effectiveness」節より

"Default effort" ／ "high" — Claude Docs「Latest models comparison」表の Default effort 行と、その Claude Opus 5 列より

"Context window" ／ "1M tokens" ／ "Max output" ／ "128K tokens" ／ "Reliable knowledge cutoff" ／ "May 2026" — Claude Docs「Latest models comparison」表の Claude Opus 5 列より

"During pre-deployment testing, our automated behavioral audit found Opus 5 to be our most aligned model to date (as shown in the graph below). It adheres to Claude’s Constitution better than Opus 4.8, Sonnet 5, or Fable 5; exhibits the lowest rates of deceptive behavior; and is the least susceptible to being tricked into misuse." ／ "On our automated behavioral audit, Opus 5 scores 2.3 on overall misaligned behavior, the lowest of our recent models." — Anthropic 公式ニュース「Alignment and safety」節より

"The model has nevertheless improved substantially on these tasks as a result of becoming more generally capable, and it comes close to Mythos 5 at finding cybersecurity vulnerabilities. However, it remains substantially behind Mythos 5 on the exploitation of those vulnerabilities—that is, in turning vulnerabilities into material cyber threats." ／ "As with its predecessor, Opus 4.8, we’ve intentionally avoided training Opus 5 on cyber tasks." ／ "Enterprises and researchers who are already part of the CVP have immediate access to a version of Opus 5 with fewer security restrictions." — Anthropic 公式ニュース「Alignment and safety」「Safeguards for Opus 5」節より