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.

Gemini 3.6 FlashGPT-5 Mini
Gemini 3.6 Flash

Google

GPT-5 Mini

OpenAI

Pricing
Input $/1M$1.50$0.25
Output $/1M$7.50$2.00
Blended $/1M (3:1)$3.00$0.688
Cache read $/1M$0.15$0.025
Cache write $/1M$0.083
Quality indices
Intelligence Index50.125.3
Coding Index69.215.6
Math Index90.7
Agentic Index38.719.4
Speed & latency
Output speed (tok/s)301111
Time to first token11.80s87.43s
Time to first answer token11.80s87.43s
Benchmarks (Artificial Analysis)
MMLU-Pro83.7%
GPQA Diamond92.8%82.8%
Humanity's Last Exam38.3%19.7%
LiveCodeBench83.8%
SciCode52.7%39.2%
AIME 202590.7%
IFBench75.4%
AA-LCR (Long Context Reasoning)69.7%68.0%
Terminal-Bench Hard33.3%
Terminal-Bench 2.177.5%3.7%
τ²-Bench (Telecom)68.4%
τ³-Bench Banking24.5%14.6%
Design Arena (Elo)
Website1,3321,152
UI components1,147
Data viz1,164
SVG1,138
3D1,096
Game dev1,187
Code categories1,148
ASCII art1,163
Specs
Context window1.05M400K
Max output tokens66K128K
Input modalitiestext, image, video, file, audiotext, image, file
TokenizerGeminiGPT