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 Sonnet 5GPT-5.5
Claude Sonnet 5

Anthropic

GPT-5.5

OpenAI

Pricing
Input $/1M$2.00$5.00
Output $/1M$10.00$30.00
Blended $/1M (3:1)$4.00$11.25
Cache read $/1M$0.20$0.50
Cache write $/1M$2.50
Quality indices
Intelligence Index53.454.8
Coding Index71.574.9
Math Index
Agentic Index46.744.9
Speed & latency
Output speed (tok/s)8692
Time to first token93.73s40.65s
Time to first answer token93.73s40.65s
Benchmarks (Artificial Analysis)
GPQA Diamond91.1%93.5%
Humanity's Last Exam39.6%44.3%
SciCode53.6%56.1%
IFBench75.9%
AA-LCR (Long Context Reasoning)70.7%74.3%
Terminal-Bench Hard60.6%
Terminal-Bench 2.180.5%84.3%
τ²-Bench (Telecom)93.9%
τ³-Bench Banking28.2%31.3%
Design Arena (Elo)
Website1,3141,280
Web apps1,3051,171
Full-stack1,2921,142
Mobile apps1,218
Android native1,2551,241
UI components1,3171,294
Data viz1,2811,293
SVG1,2391,273
3D1,3211,250
Game dev1,3451,343
Agentic game dev1,2411,191
Godot game dev1,2571,204
HTML slides1,2331,083
PPTX slides1,157
Python→PPTX slides1,2521,152
Agentic slides1,150
Agentic HTML slides1,084
Agentic slides (HTML)1,077
Agentic slides (Python PPTX)1,155
Code categories1,3121,284
ASCII art1,2301,288
Specs
Context window1M1.05M
Max output tokens128K128K
Input modalitiestext, image, filefile, image, text
TokenizerClaudeGPT