Claude 3.5 Sonnet (Anthropic) AI Model: Benchmark Scores, Pricing & VRAM Specs | ModelAnalysis.si

      Anthropic • COMMERCIAL APIClaude 3.5 SonnetAnthropic 2024-era benchmark pioneer that established modern SWE-bench Verified coding standards and multi-step agentic workflows.

            Metric Dimension
            Verified Value
            Evaluation Benchmark
          
            Chatbot Arena Elo
            1335 pts
            LMSYS Live Battles
          
            Coding Index
            93.7 / 100
            SWE-bench Verified
          
            Agentic Tool-Use
            92 / 100
            Multi-Turn Tool Calls
          
            Input Rate
            $3.00 / 1M
            Commercial Token API
          
            Output Rate
            $15.00 / 1M
            Generation Billing
          
            Context Horizon
            200k
            Maximum Token Window