That’s a six-point jump over Sonnet 4.6 (47 points), but Sonnet 5 chews through far more tokens to get there.<\/p>\n Same token prices, double the real cost<\/p>\n On paper, Sonnet 5 keeps the same token prices as its predecessor: $3 per million input tokens and $15 per million output tokens, while Opus 4.8 sits at $5 and $25. Yet according to Artificial Analysis, an average task in the Intelligence Index costs $2.29 with Sonnet 5, versus about $1.97 with Opus 4.8.<\/p>\n At the maximum performance setting (“max”), Sonnet 5 burns through about 40 percent more output tokens per task than Sonnet 4.6. In agent-based knowledge work benchmarks like AA-Briefcase and\u00a0GDPval-AA<\/a>, it runs about three times as many agent loops as its predecessor. Sonnet 4.6 cost about $1.20 per task. That’s nearly doubled, even though Sonnet 5 beats Opus 4.8 on some of these tasks.<\/p>\n Anthropic is running a promotional rate of $2 or $10 per million tokens through September 1, but Artificial Analysis based its results on regular prices.<\/p>\n Complex reasoning still exposes Sonnet 5’s limits<\/p>\n Sonnet 5 still falls short of larger models on reasoning- and knowledge-heavy benchmarks. On CritPt, a frontier physics reasoning test from Argonne National Labs and the University of Illinois, it scored 17 percent. That’s 14 points above its predecessor but below GLM-5.2, Claude Opus, Fable, and GPT-5.5 in their higher configurations.<\/p>\n Elsewhere, Sonnet 5 shows solid gains over Sonnet 4.6: a 9-point jump on Terminal-Bench v2.1, 10 points on Humanity’s Last Exam, and 7 points on SciCode. Scores on the remaining evaluations stayed roughly flat.<\/p>\n Anthropic keeps raising prices without saying so<\/p>\n Anthropic has done this before. When\u00a0Opus 4.7 launched<\/a>, token prices stayed flat on paper, but a new tokenizer chopped the same text into “approximately 30%” more tokens<\/a>, inflating the real bill. Developer Abhishek Ray measured a 1.325x to 1.47x increase, and a community analysis of over 483 submissions found a 37.4 percent jump in tokens per request. With Sonnet 5, the tokenizer issue is compounded by the model’s more agentic behavior, which eats through far more tokens per task.<\/p>\n Anthropic’s models keep getting pricier with each generation, sometimes dramatically so, yet the official price lists don’t reflect it. That kind of hidden cost creep is a hard sell when Chinese competitors like\u00a0Deepseek V4 Pro<\/a>\u00a0and\u00a0GLM-5.2<\/a>\u00a0offer competitive performance at a fraction of the cost in the mid-range segment<\/a> where Sonnet sits.<\/p>\n![\"\"](\"https:\/\/www.europesays.com\/ai\/wp-content\/uploads\/2026\/07\/aa_sonnet5_overall.png\")
<\/a>In the Artificial Analysis Intelligence Index v4.1, which aggregates several benchmarks, Claude Sonnet 5 ranks fifth with 53 points. | Image: Artificial Analysis<\/p>\n![\"\"](\"https:\/\/www.europesays.com\/ai\/wp-content\/uploads\/2026\/07\/aa_sonnet5_costprice.png\")
<\/a>Cost per task in the Intelligence Index shows Sonnet 5 at $2.29, more expensive than Opus 4.8 at $1.97. | Image: Artificial Analysis<\/p>\n