Skip to content
Tech News
← Back to articles

Claude Sonnet 5 – benchmark results

read original more articles
Why This Matters

Claude Sonnet 5 (Adaptive Reasoning, Max Effort) stands out as a highly intelligent and fast model, achieving top scores on the Artificial Analysis Intelligence Index. However, its high cost and verbosity may impact its adoption for cost-sensitive applications. Its performance highlights ongoing advancements in AI capabilities, emphasizing the trade-offs between speed, cost, and output quality in the industry.

Key Takeaways

Claude Sonnet 5 (Adaptive Reasoning, Max Effort) is amongst the leading models in intelligence, but somewhat expensive when comparing to other models of similar price. It's also faster than average, however very verbose. The model supports text and image input, outputs text, and has a 1m tokens context window.

Claude Sonnet 5 (Adaptive Reasoning, Max Effort) scores 53 on the Artificial Analysis Intelligence Index, placing it well above average among comparable models (averaging 29 ). When evaluating the Intelligence Index, it generated 300M tokens, which is very verbose in comparison to the average of 87M .

Pricing for Claude Sonnet 5 (Adaptive Reasoning, Max Effort) is $3.00 per 1M input tokens ( somewhat expensive , average: $1.60 ) and $15.00 per 1M output tokens ( somewhat expensive , average: $8.10 ). In total, it cost $6015.18 to evaluate Claude Sonnet 5 (Adaptive Reasoning, Max Effort) on the Intelligence Index.

At 91 tokens per second, Claude Sonnet 5 (Adaptive Reasoning, Max Effort) is faster than average ( 74 ).