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-5.1-Codex-Mini
Gemini 3.6 Flash

Google

GPT-5.1-Codex-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 Index50.130.6
Coding Index69.2
Math Index91.7
Agentic Index38.7
Speed & latency
Output speed (tok/s)301210
Time to first token11.80s4.92s
Time to first answer token11.80s4.92s
Benchmarks (Artificial Analysis)
MMLU-Pro82.0%
GPQA Diamond92.8%81.3%
Humanity's Last Exam38.3%16.9%
LiveCodeBench83.6%
SciCode52.7%42.6%
AIME 202591.7%
IFBench67.9%
AA-LCR (Long Context Reasoning)69.7%62.7%
Terminal-Bench Hard33.3%
Terminal-Bench 2.177.5%
τ²-Bench (Telecom)62.9%
τ³-Bench Banking24.5%
Design Arena (Elo)
Website1,3321,138
UI components1,122
Data viz1,133
SVG1,024
3D1,048
Game dev1,151
Code categories1,127
ASCII art1,147
Specs
Context window1.05M400K
Max output tokens66K100K
Input modalitiestext, image, video, file, audioimage, text
TokenizerGeminiGPT