AiCostCompare

Compare models

Pick up to 4 models for a side-by-side spec sheet. Hover any dotted metric name for what the test measures. Best value in each row is highlighted.

Claude Haiku 4.5GPT-5.2
Claude Haiku 4.5

Anthropic

GPT-5.2

OpenAI

Pricing
Input $/1M$1.00$1.75
Output $/1M$5.00$14.00
Blended $/1M (3:1)$2.00$4.81
Cache read $/1M$0.10$0.175
Cache write $/1M$1.25
Quality indices
Intelligence Index29.642.2
Coding Index43.9
Math Index99
Agentic Index16.4
Speed & latency
Output speed (tok/s)85
Time to first token111.04s
Time to first answer token111.04s
Benchmarks (Artificial Analysis)
MMLU-Pro87.4%
GPQA Diamond90.3%
Humanity's Last Exam35.4%
LiveCodeBench88.9%
SciCode52.1%
AIME 202599.0%
IFBench75.4%
AA-LCR (Long Context Reasoning)72.7%
Terminal-Bench Hard47.0%
τ²-Bench (Telecom)84.8%
Design Arena (Elo)
Website1,1491,222
Web apps1,142
Full-stack1,100
Mobile apps1,167
Android native1,052
UI components1,1421,231
Data viz1,1601,238
SVG1,0721,185
3D1,1311,138
Game dev1,1551,253
Godot game dev1,142
Code categories1,1481,203
ASCII art1,1821,194
Specs
Context window200K400K
Max output tokens64K128K
Input modalitiestext, image, filefile, image, text
TokenizerClaudeGPT