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 5GPT-5.6 Sol
Claude Opus 5

Anthropic

GPT-5.6 Sol

OpenAI

Pricing
Input $/1M$5.00$2.00
Output $/1M$25.00$10.00
Blended $/1M (3:1)$10.00$4.00
Cache read $/1M$0.50$0.20
Cache write $/1M$6.25$2.50
Quality indices
Intelligence Index50.847
Coding Index7877.4
Math Index
Agentic Index56.550.2
Speed & latency
Output speed (tok/s)5465
Time to first token25.13s64.46s
Time to first answer token25.13s64.46s
Benchmarks (Artificial Analysis)
GPQA Diamond93.2%94.1%
Humanity's Last Exam54.9%49.5%
SciCode56.4%57.1%
IFBench72.7%
AA-LCR (Long Context Reasoning)79.3%84.0%
Terminal-Bench Hard65.9%
Terminal-Bench 2.189.1%88.0%
τ²-Bench (Telecom)85.1%
τ³-Bench Banking42.1%44.3%
Design Arena (Elo)
Website1,321
Web apps1,278
Full-stack1,314
Mobile apps1,348
Android native1,266
UI components1,360
Data viz1,353
SVG1,345
3D1,360
Game dev1,361
Agentic game dev1,261
Godot game dev1,275
Python→PPTX slides1,265
Code categories1,338
ASCII art1,390
Specs
Context window1M1.05M
Max output tokens128K128K
Input modalitiestext, image, filefile, image, text
TokenizerClaudeGPT