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 4.5Grok 4.5
Claude Haiku 4.5

Anthropic

Grok 4.5

xAI

Pricing
Input $/1M$1.00$2.00
Output $/1M$5.00$6.00
Blended $/1M (3:1)$2.00$3.00
Cache read $/1M$0.10$0.30
Cache write $/1M$1.25
Quality indices
Intelligence Index29.653.8
Coding Index43.972.4
Math Index
Agentic Index16.445.7
Speed & latency
Output speed (tok/s)73
Time to first token9.69s
Time to first answer token9.69s
Benchmarks (Artificial Analysis)
GPQA Diamond93.1%
Humanity's Last Exam40.3%
SciCode54.1%
AA-LCR (Long Context Reasoning)67.7%
Terminal-Bench 2.181.6%
τ³-Bench Banking32.6%
Design Arena (Elo)
Website1,1491,323
Web apps1,270
Full-stack1,302
Android native1,263
UI components1,1421,331
Data viz1,1601,302
SVG1,072
3D1,1311,329
Game dev1,1551,330
Agentic game dev1,227
Godot game dev1,297
HTML slides1,240
Python→PPTX slides1,230
Code categories1,1481,323
ASCII art1,182
Specs
Context window200K500K
Max output tokens64K
Input modalitiestext, image, filetext, image, file
TokenizerClaudeGrok