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 5Grok 4.6
Claude Sonnet 5

Anthropic

Grok 4.6

xAI

Pricing
Input $/1M$2.00$2.00
Output $/1M$10.00$6.00
Blended $/1M (3:1)$4.00$3.00
Cache read $/1M$0.20$0.50
Cache write $/1M$2.50
Quality indices
Intelligence Index38.244.3
Coding Index71.576.8
Math Index
Agentic Index43.653
Speed & latency
Output speed (tok/s)8258
Time to first token118.14s34.50s
Time to first answer token118.14s34.50s
Benchmarks (Artificial Analysis)
GPQA Diamond91.1%94.9%
Humanity's Last Exam41.3%42.9%
SciCode54.3%56.5%
AA-LCR (Long Context Reasoning)82.0%80.3%
Terminal-Bench 2.180.5%88.4%
τ³-Bench Banking37.3%50.7%
Design Arena (Elo)
Website1,2881,304
Web apps1,2601,264
Full-stack1,2601,274
Mobile apps1,2491,267
Android native1,2401,301
UI components1,2991,305
Data viz1,2601,303
SVG1,2121,263
3D1,2891,305
Game dev1,3131,321
Agentic game dev1,2271,210
Godot game dev1,238
HTML slides1,2201,253
Python→PPTX slides1,2161,242
Code categories1,2931,309
ASCII art1,2261,297
Specs
Context window1M500K
Max output tokens128K450K
Input modalitiestext, image, filetext, image, file
TokenizerClaudeGrok