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-5.3-Codex
Gemini 3.6 Flash

Google

GPT-5.3-Codex

OpenAI

Pricing
Input $/1M$0.75$1.75
Output $/1M$3.75$14.00
Blended $/1M (3:1)$1.50$4.81
Cache read $/1M$0.075$0.175
Cache write $/1M$0.042
Quality indices
Intelligence Index3432.5
Coding Index69.2
Math Index
Agentic Index29
Speed & latency
Output speed (tok/s)265154
Time to first token21.43s36.11s
Time to first answer token21.43s36.11s
Benchmarks (Artificial Analysis)
GPQA Diamond92.8%91.5%
Humanity's Last Exam40.8%42.5%
SciCode53.4%
IFBench75.4%
AA-LCR (Long Context Reasoning)80.0%83.3%
Terminal-Bench Hard53.0%
Terminal-Bench 2.177.5%
τ²-Bench (Telecom)86.0%
τ³-Bench Banking29.9%
Design Arena (Elo)
Website1,3121,175
Web apps1,2111,048
Full-stack1,188993
Mobile apps1,2281,083
Android native1,2131,084
UI components1,3181,153
Data viz1,3111,179
SVG1,152
3D1,3021,037
Game dev1,2861,185
Agentic game dev1,180
Godot game dev1,124
HTML slides1,152
Python→PPTX slides1,146
Code categories1,3051,160
ASCII art1,3041,170
Specs
Context window1.05M400K
Max output tokens66K128K
Input modalitiestext, image, video, file, audiotext, image, file
TokenizerGeminiGPT