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 4.6GPT-5.6 Sol
Claude Sonnet 4.6

Anthropic

GPT-5.6 Sol

OpenAI

Pricing
Input $/1M$3.00$5.00
Output $/1M$15.00$30.00
Blended $/1M (3:1)$6.00$11.25
Cache read $/1M$0.30$0.50
Cache write $/1M$3.75$6.25
Quality indices
Intelligence Index35.958.9
Coding Index6377.4
Math Index
Agentic Index40.854
Speed & latency
Output speed (tok/s)5967
Time to first token1.15s120.38s
Time to first answer token1.15s120.38s
Benchmarks (Artificial Analysis)
GPQA Diamond79.9%94.1%
Humanity's Last Exam13.2%47.2%
SciCode46.9%56.1%
IFBench41.2%72.7%
AA-LCR (Long Context Reasoning)57.7%73.7%
Terminal-Bench Hard46.2%65.9%
Terminal-Bench 2.188.0%
τ²-Bench (Telecom)79.5%85.1%
τ³-Bench Banking33.0%
Design Arena (Elo)
Website1,312
Web apps1,245
Full-stack1,268
Mobile apps1,272
Android native1,211
UI components1,313
Data viz1,315
SVG1,244
3D1,292
Game dev1,315
Agentic game dev1,210
Godot game dev1,226
Code categories1,309
ASCII art1,271
Specs
Context window1M1.05M
Max output tokens128K128K
Input modalitiestext, image, filefile, image, text
TokenizerClaudeGPT