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 4.6Muse Spark 1.1
Claude Opus 4.6

Anthropic

Muse Spark 1.1

Meta

Pricing
Input $/1M$5.00$1.25
Output $/1M$25.00$4.25
Blended $/1M (3:1)$10.00$2.00
Cache read $/1M$0.50$0.15
Cache write $/1M$6.25
Quality indices
Intelligence Index37.850.6
Coding Index71.3
Math Index
Agentic Index37.5
Speed & latency
Output speed (tok/s)54
Time to first token1.89s
Time to first answer token1.89s
Benchmarks (Artificial Analysis)
GPQA Diamond84.0%
Humanity's Last Exam18.6%
SciCode45.7%
IFBench44.6%
AA-LCR (Long Context Reasoning)58.3%
Terminal-Bench Hard48.5%
τ²-Bench (Telecom)84.8%
Design Arena (Elo)
Website1,3231,296
Web apps1,2611,264
Full-stack1,279
Mobile apps1,280
Android native1,195
UI components1,3361,302
Data viz1,3221,324
SVG1,274
3D1,3351,305
Game dev1,3371,327
Agentic game dev1,196
Godot game dev1,148
HTML slides1,223
Python→PPTX slides1,175
Code categories1,3271,304
ASCII art1,298
Specs
Context window1M1.05M
Max output tokens128K
Input modalitiestext, image, filetext, image, video, file, audio
TokenizerClaudeOther