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 5Muse Spark 1.2
Claude Sonnet 5

Anthropic

Muse Spark 1.2

Meta

Pricing
Input $/1M$2.00$1.25
Output $/1M$10.00$4.25
Blended $/1M (3:1)$4.00$2.00
Cache read $/1M$0.20$0.15
Cache write $/1M$2.50
Quality indices
Intelligence Index38.239.6
Coding Index71.572.2
Math Index
Agentic Index43.643.2
Speed & latency
Output speed (tok/s)82
Time to first token118.14s
Time to first answer token118.14s
Benchmarks (Artificial Analysis)
GPQA Diamond91.1%
Humanity's Last Exam41.3%
SciCode54.3%
AA-LCR (Long Context Reasoning)82.0%
Terminal-Bench 2.180.5%
τ³-Bench Banking37.3%
Design Arena (Elo)
Website1,2881,321
Web apps1,2601,240
Full-stack1,2601,219
Mobile apps1,2491,196
Android native1,2401,236
UI components1,2991,330
Data viz1,2601,365
SVG1,2121,313
3D1,2891,332
Game dev1,3131,323
Agentic game dev1,2271,179
Godot game dev1,238
HTML slides1,2201,137
Python→PPTX slides1,2161,198
Code categories1,2931,326
ASCII art1,2261,323
Specs
Context window1M1.05M
Max output tokens128K944K
Input modalitiestext, image, filetext, image, video, file, audio
TokenizerClaudeOther