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 4.5GPT-5 Mini
Claude Haiku 4.5

Anthropic

GPT-5 Mini

OpenAI

Pricing
Input $/1M$1.00$0.25
Output $/1M$5.00$2.00
Blended $/1M (3:1)$2.00$0.688
Cache read $/1M$0.10$0.025
Cache write $/1M$1.25
Quality indices
Intelligence Index29.625.3
Coding Index43.915.6
Math Index90.7
Agentic Index16.419.4
Speed & latency
Output speed (tok/s)109
Time to first token84.93s
Time to first answer token84.93s
Benchmarks (Artificial Analysis)
MMLU-Pro83.7%
GPQA Diamond82.8%
Humanity's Last Exam19.7%
LiveCodeBench83.8%
SciCode39.2%
AIME 202590.7%
IFBench75.4%
AA-LCR (Long Context Reasoning)68.0%
Terminal-Bench Hard33.3%
Terminal-Bench 2.13.7%
τ²-Bench (Telecom)68.4%
τ³-Bench Banking14.6%
Design Arena (Elo)
Website1,1491,152
UI components1,1421,147
Data viz1,1601,164
SVG1,0721,138
3D1,1311,096
Game dev1,1551,187
Code categories1,1481,148
ASCII art1,1821,163
Specs
Context window200K400K
Max output tokens64K128K
Input modalitiestext, image, filetext, image, file
TokenizerClaudeGPT