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 4.6Hy3 preview
Claude Opus 4.6

Anthropic

Hy3 preview

Tencent

Pricing
Input $/1M$5.00$0.063
Output $/1M$25.00$0.21
Blended $/1M (3:1)$10.00$0.10
Cache read $/1M$0.50$0.021
Cache write $/1M$6.25
Quality indices
Intelligence Index37.833.6
Coding Index58.8
Math Index
Agentic Index30.7
Speed & latency
Output speed (tok/s)54144
Time to first token1.89s1.68s
Time to first answer token1.89s15.54s
Benchmarks (Artificial Analysis)
GPQA Diamond84.0%86.7%
Humanity's Last Exam18.6%25.5%
SciCode45.7%41.2%
IFBench44.6%63.1%
AA-LCR (Long Context Reasoning)58.3%54.7%
Terminal-Bench Hard48.5%34.1%
τ²-Bench (Telecom)84.8%92.7%
Design Arena (Elo)
Website1,323
Web apps1,261
Full-stack1,279
Mobile apps1,280
Android native1,195
UI components1,336
Data viz1,322
SVG1,274
3D1,335
Game dev1,337
Code categories1,327
ASCII art1,298
Specs
Context window1M262K
Max output tokens128K
Input modalitiestext, image, filetext
TokenizerClaudeOther