Claude 4.5 Haiku (Reasoning)

Anthropic

ReasoningVision ModelProprietary

Analysis of Anthropic's Claude 4.5 Haiku (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: Oct 15, 2025
Knowledge Cutoff: Jul 01, 2025
Window: 200k

PricingPer 1M tokens

Input: $1
Output: $5
Blended 3:1: $2

Capabilities

Speed: 110 t/s
Input
Output
Reasoning tokens

Latency

TTFT: 16.94 ms
500 token response: 21.48 s

Benchmarks

Reasoning: ●●○○○
Math: ●●●●○
Coding: ●●○○○
MMLU Pro: 76.0%
GPQA: 67.2%
HLE: 9.7%
SciCode: 43.3%
AIME: 83.7%
LiveCodeBench: 61.5%

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