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 4.6GPT-5 Mini
Claude Opus 4.6

Anthropic

GPT-5 Mini

OpenAI

Pricing
Input $/1M$5.00$0.25
Output $/1M$25.00$2.00
Blended $/1M (3:1)$10.00$0.688
Cache read $/1M$0.50$0.025
Cache write $/1M$6.25
Quality indices
Intelligence Index37.825.3
Coding Index15.6
Math Index90.7
Agentic Index19.4
Speed & latency
Output speed (tok/s)54109
Time to first token1.89s84.93s
Time to first answer token1.89s84.93s
Benchmarks (Artificial Analysis)
MMLU-Pro83.7%
GPQA Diamond84.0%82.8%
Humanity's Last Exam18.6%19.7%
LiveCodeBench83.8%
SciCode45.7%39.2%
AIME 202590.7%
IFBench44.6%75.4%
AA-LCR (Long Context Reasoning)58.3%68.0%
Terminal-Bench Hard48.5%33.3%
Terminal-Bench 2.13.7%
τ²-Bench (Telecom)84.8%68.4%
τ³-Bench Banking14.6%
Design Arena (Elo)
Website1,3231,152
Web apps1,261
Full-stack1,279
Mobile apps1,280
Android native1,195
UI components1,3361,147
Data viz1,3221,164
SVG1,2741,138
3D1,3351,096
Game dev1,3371,187
Code categories1,3271,148
ASCII art1,2981,163
Specs
Context window1M400K
Max output tokens128K128K
Input modalitiestext, image, filetext, image, file
TokenizerClaudeGPT