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 Flasho3
Gemini 3.6 Flash

Google

o3

OpenAI

Pricing
Input $/1M$1.50$2.00
Output $/1M$7.50$8.00
Blended $/1M (3:1)$3.00$3.50
Cache read $/1M$0.15$0.50
Cache write $/1M$0.083
Quality indices
Intelligence Index50.130.4
Coding Index69.2
Math Index88.3
Agentic Index38.7
Speed & latency
Output speed (tok/s)301159
Time to first token11.80s4.84s
Time to first answer token11.80s4.84s
Benchmarks (Artificial Analysis)
MMLU-Pro85.3%
GPQA Diamond92.8%82.7%
Humanity's Last Exam38.3%20.0%
LiveCodeBench80.8%
SciCode52.7%41.0%
MATH-50099.2%
AIME90.3%
AIME 202588.3%
IFBench71.4%
AA-LCR (Long Context Reasoning)69.7%69.3%
Terminal-Bench Hard37.1%
Terminal-Bench 2.177.5%
τ²-Bench (Telecom)80.7%
τ³-Bench Banking24.5%
Design Arena (Elo)
Website1,3321,064
UI components1,060
Data viz1,200
Game dev1,093
Code categories1,053
Specs
Context window1.05M200K
Max output tokens66K100K
Input modalitiestext, image, video, file, audioimage, text, file
TokenizerGeminiGPT