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 Turbo
Gemini 3.6 Flash

Google

GPT-4 Turbo

OpenAI

Pricing
Input $/1M$1.50$10.00
Output $/1M$7.50$30.00
Blended $/1M (3:1)$3.00$15.00
Cache read $/1M$0.15
Cache write $/1M$0.083
Quality indices
Intelligence Index50.17.9
Coding Index69.221.5
Math Index
Agentic Index38.7
Speed & latency
Output speed (tok/s)31140
Time to first token12.80s1.26s
Time to first answer token12.80s1.26s
Benchmarks (Artificial Analysis)
MMLU-Pro69.4%
GPQA Diamond92.8%
Humanity's Last Exam38.3%3.3%
LiveCodeBench29.1%
SciCode52.7%31.9%
MATH-50073.7%
AIME15.0%
AA-LCR (Long Context Reasoning)69.7%
Terminal-Bench 2.177.5%
τ³-Bench Banking24.5%
Design Arena (Elo)
Website1,332
Specs
Context window1.05M128K
Max output tokens66K4K
Input modalitiestext, image, video, file, audiotext, image
TokenizerGeminiGPT