Claude 4.5 Sonnet (Non-reasoning)

Anthropic

Vision ModelProprietary

Analysis of Anthropic's Claude 4.5 Sonnet (Non-reasoning) and comparison to other AI models across key metrics including quality, price, performance (tokens per second & time to first token), context window & more.

Context

Release Date: Sep 29, 2025
Knowledge Cutoff: Jul 01, 2025
Window: 1M

PricingPer 1M tokens

Input: $3
Output: $15
Blended 3:1: $6

Capabilities

Speed: 40 t/s
Input
Output
Reasoning tokens

Latency

TTFT: 1.39 ms
500 token response: 13.92 s

Benchmarks

Intelligence: ●●○○○
Math: ●●○○○
Coding: ●●○○○
MMLU Pro: 86.0%
GPQA: 72.7%
HLE: 7.1%
SciCode: 42.8%
AIME: 37.0%
LiveCodeBench: 59.0%

Analysis of Anthropic's Claude 4.5 Sonnet (Non-reasoning) and comparison to other AI models across key metrics including quality, price, performance (tokens per second & time to first token), context window & more.