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-4.1 Mini (batch)
Gemini 3.6 Flash

Google

GPT-4.1 Mini (batch)

OpenAI

Pricing
Input $/1M$0.75$0.20
Output $/1M$3.75$0.80
Blended $/1M (3:1)$1.50$0.35
Cache read $/1M$0.075$0.05
Cache write $/1M$0.042
Quality indices
Intelligence Index3410.2
Coding Index69.220.2
Math Index46.3
Agentic Index29
Speed & latency
Output speed (tok/s)2650
Time to first token21.43s0s
Time to first answer token21.43s0s
Benchmarks (Artificial Analysis)
MMLU-Pro78.1%
GPQA Diamond92.8%66.4%
Humanity's Last Exam40.8%5.0%
LiveCodeBench48.3%
SciCode53.4%
MATH-50092.5%
AIME43.0%
AIME 202546.3%
IFBench38.3%
AA-LCR (Long Context Reasoning)80.0%44.0%
Terminal-Bench Hard7.6%
Terminal-Bench 2.177.5%10.1%
τ²-Bench (Telecom)52.9%
τ³-Bench Banking29.9%5.4%
Design Arena (Elo)
Website1,3121,010
Web apps1,211
Full-stack1,188
Mobile apps1,228
Android native1,213
UI components1,318976
Data viz1,3111,047
3D1,302865
Game dev1,2861,094
Agentic game dev1,180
HTML slides1,152
Python→PPTX slides1,146
Code categories1,3051,009
ASCII art1,304
Specs
Context window1.05M1.05M
Max output tokens66K33K
Input modalitiestext, image, video, file, audioimage, text, file
TokenizerGeminiGPT