COMPARE LLM MODELS

Claude 3 Haiku

vs

GPT-3.5 Turbo

Compare these models on reasoning, tool use, math, and coding tasks. Check their pricing, speed, and overall performance side by side.

Basic Comparison

Model

Context size

Cutoff date

Input/Output cost

Max output tokens

Latency (TTFT)

Throughput

Claude 3 Haiku

200,000

Apr 2024

$0.25

/

$1.25

4096

0.55s

133 t/s

GPT-3.5 Turbo

16,400

Sept 2023

$0.5

/

$1.5

4096

0.37s

84 t/s

Standard Benchmarks

Dynamic Chart

Go to LLM Leaderboard

Compare

Claude 3 Haiku

with other models

Claude 3.5 Sonnet