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 Opus 4.7GPT-5.6 Terra
Claude Opus 4.7

Anthropic

GPT-5.6 Terra

OpenAI

Pricing
Input $/1M$5.00$2.50
Output $/1M$25.00$15.00
Blended $/1M (3:1)$10.00$5.63
Cache read $/1M$0.50$0.25
Cache write $/1M$6.25$3.13
Quality indices
Intelligence Index53.555
Coding Index73.676.7
Math Index
Agentic Index44.447.4
Speed & latency
Output speed (tok/s)61149
Time to first token16.85s104.73s
Time to first answer token16.85s104.73s
Benchmarks (Artificial Analysis)
GPQA Diamond91.4%92.5%
Humanity's Last Exam39.6%41.8%
SciCode54.5%53.9%
IFBench58.6%71.2%
AA-LCR (Long Context Reasoning)70.3%74.0%
Terminal-Bench Hard51.5%57.6%
Terminal-Bench 2.183.1%88.0%
τ²-Bench (Telecom)88.6%86.3%
τ³-Bench Banking28.9%31.8%
Design Arena (Elo)
Website1,322
Web apps1,311
Full-stack1,503
Android native1,266
UI components1,345
Data viz1,315
SVG1,272
3D1,304
Game dev1,336
Agentic game dev1,259
Godot game dev1,266
HTML slides1,240
PPTX slides1,333
Python→PPTX slides1,336
Agentic slides1,334
Agentic HTML slides1,243
Agentic slides (HTML)1,242
Agentic slides (Python PPTX)1,331
Code categories1,321
ASCII art1,326
Specs
Context window1M1.05M
Max output tokens128K128K
Input modalitiestext, image, filefile, image, text
TokenizerClaudeGPT