{"slug": "claude-sonnet-5-strong-agentic-performance-at-a-higher-cost-per-task", "title": "Claude Sonnet 5: strong agentic performance at a higher cost per task", "summary": "Anthropic's Claude Sonnet 5 achieves a score of 53 on the Artificial Analysis Intelligence Index, matching GPT-5.5 with high reasoning but costing $2.29 per task—15% more than Opus 4.8—due to increased token usage. The model excels in agentic knowledge work, outperforming Opus 4.8 on AA-Briefcase and GDPval-AA, but lags behind larger models on heavy reasoning benchmarks.", "body_md": "[All articles](/articles)\n\nJune 30, 2026\n\n# Claude Sonnet 5: strong agentic performance at a higher cost per task\n\n**Claude Sonnet 5 achieves 53 on the Artificial Analysis Intelligence Index, but without promotional pricing will cost more per task than Opus 4.8**\n\nWe supported Anthropic to evaluate Claude Sonnet 5 ahead of release: with max effort it improves 6 points over Sonnet 4.6 to achieve the same Intelligence Index as GPT-5.5 with high reasoning, but remains behind Opus 4.7 and 4.8\n\n**Key takeaways:**\n\n➤ **Claude Sonnet 5 is the #5 model on the Artificial Analysis Intelligence Index**, only 2-3 points behind GPT-5.5 (xhigh) and Opus 4.8 (max)\n\n➤ **With max effort, Sonnet 5 works harder than previous Anthropic models:** it used ~40% more output tokens per Intelligence Index task than Sonnet 4.6, and ~3x the agentic turns for our knowledge work evaluations AA-Briefcase and GDPval-AA. This behavior scales well with the ‘effort’ setting, with the max effort using around 6x more turns than low effort on GDPval-AA\n\n**➤ Claude Sonnet 5 costs more per task than Opus 4.8 before accounting for promotional pricing**: Claude Sonnet 5 costs $2.29 per task on the Intelligence Index, a ~2x increase compared to Sonnet 4.6 and ~15% more than Claude Opus 4.8. This is driven entirely by increased token usage. Sonnet 5 retains the same $3/$15 per 1M input/output token pricing as Sonnet 4.6 (compared to $5/$25 for Opus 4.8), however Anthropic is offering a one-third reduction to $2/$10 until September 1. Our results use standard $3/$15 pricing\n\n➤ **Sonnet 5 matches or outperforms Opus 4.8 on agentic knowledge work tasks:** on both AA-Briefcase and GDPval-AA, Claude Sonnet 5 sits just ahead of Opus 4.8, trailing only Claude Fable 5 (which is not currently generally available). These benchmarks test the ability of models to produce accurate and well-presented professional outputs using our open source reference agent harness, Stirrup\n\n➤ **For reasoning and knowledge-heavy tasks, Sonnet still sits behind its larger siblings:** despite substantial gains across many evaluations, heavy reasoning and knowledge benchmarks still show Opus 4.8 ahead of Sonnet 5. On CritPt, a frontier physics reasoning benchmark developed by researchers at Argonne and UIUC, Sonnet 5 scores 17% - this is 14 points higher than its predecessor, but behind GLM-5.2, Claude Opus and Fable, and GPT-5.5 (xhigh and Pro)\n\n➤ Sonnet 5 also showed significant improvements over Sonnet 4.6 on Terminal-Bench v2.1 (+9 points), Humanity’s Last Exam (+10 points), and SciCode (+7 points), with relatively flat scores elsewhere\n\n**Other key model details:**\n\n➤ Context window of 1 million tokens (equivalent to Sonnet 4.6)\n\n➤ Pricing of $3/$15 per 1M tokens of input/output (reduced to $2/$10 until September 1); cache pricing remains at a 25% premium for cache writes ($3.75 per million tokens) with 5-minute time to live, and 90% discount for cache hits ($0.3 per million tokens)\n\n➤ Effort remains the recommended way of configuring model performance and latency. Sonnet 5 adds an additional ‘xhigh’ effort setting relative to Sonnet 4.6, matching the 5 effort levels available on Opus 4.8 (max, xhigh, high, medium, low)\n\nCompare Claude Sonnet 5 with other leading models at: [https://artificialanalysis.ai/models/claude-sonnet-5](https://artificialanalysis.ai/models/claude-sonnet-5)\n\n#### Read the latest\n\n### Measuring time per task in AA-Briefcase\n\nAgentic knowledge work can take frontier models over 20 minutes per task, as measured in AA-Briefcase, our new benchmark\n\nJune 24, 2026\n\n### Announcing the Artificial Analysis Speech to Speech Index\n\nAnnouncing the Artificial Analysis Speech to Speech Index, our new synthesis metric for native Speech to Speech model quality, comprising of Big Bench Audio, Full Duplex Bench, and 𝜏-Voice\n\nJune 23, 2026\n\n### Announcing AA-Briefcase: a frontier knowledge work evaluation\n\nAA-Briefcase is a new benchmark for testing models on realistic knowledge work tasks in complex projects built by industry experts. Models are evaluated on multi-week knowledge work projects, each with many linked tasks and thousands of input source files, combining rubric and pairwise grading to evaluate verifiable task success, analytical quality, and presentation quality.\n\nJune 18, 2026", "url": "https://wpnews.pro/news/claude-sonnet-5-strong-agentic-performance-at-a-higher-cost-per-task", "canonical_source": "https://artificialanalysis.ai/articles/claude-sonnet-5-agentic-cost", "published_at": "2026-06-30 23:35:07+00:00", "updated_at": "2026-06-30 23:49:30.836685+00:00", "lang": "en", "topics": ["large-language-models", "ai-agents", "ai-products", "ai-research"], "entities": ["Anthropic", "Claude Sonnet 5", "Opus 4.8", "GPT-5.5", "Artificial Analysis", "AA-Briefcase", "GDPval-AA", "Claude Fable 5"], "alternates": {"html": "https://wpnews.pro/news/claude-sonnet-5-strong-agentic-performance-at-a-higher-cost-per-task", "markdown": "https://wpnews.pro/news/claude-sonnet-5-strong-agentic-performance-at-a-higher-cost-per-task.md", "text": "https://wpnews.pro/news/claude-sonnet-5-strong-agentic-performance-at-a-higher-cost-per-task.txt", "jsonld": "https://wpnews.pro/news/claude-sonnet-5-strong-agentic-performance-at-a-higher-cost-per-task.jsonld"}}