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 Haiku 4.5Claude Sonnet 5
Claude Haiku 4.5

Anthropic

Claude Sonnet 5

Anthropic

Pricing
Input $/1M$1.00$2.00
Output $/1M$5.00$10.00
Blended $/1M (3:1)$2.00$4.00
Cache read $/1M$0.10$0.20
Cache write $/1M$1.25$2.50
Quality indices
Intelligence Index29.653.4
Coding Index43.971.5
Math Index
Agentic Index16.446.7
Speed & latency
Output speed (tok/s)86
Time to first token93.73s
Time to first answer token93.73s
Benchmarks (Artificial Analysis)
GPQA Diamond91.1%
Humanity's Last Exam39.6%
SciCode53.6%
AA-LCR (Long Context Reasoning)70.7%
Terminal-Bench 2.180.5%
τ³-Bench Banking28.2%
Design Arena (Elo)
Website1,1491,314
Web apps1,305
Full-stack1,292
Android native1,255
UI components1,1421,317
Data viz1,1601,281
SVG1,0721,239
3D1,1311,321
Game dev1,1551,345
Agentic game dev1,241
Godot game dev1,257
HTML slides1,233
Python→PPTX slides1,252
Code categories1,1481,312
ASCII art1,1821,230
Specs
Context window200K1M
Max output tokens64K128K
Input modalitiestext, image, filetext, image, file
TokenizerClaudeClaude