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.

MiniMax M2.5GPT-5.6 Sol
MiniMax M2.5

MiniMax

GPT-5.6 Sol

OpenAI

Pricing
Input $/1M$0.15$5.00
Output $/1M$0.90$30.00
Blended $/1M (3:1)$0.337$11.25
Cache read $/1M$0.05$0.50
Cache write $/1M$6.25
Quality indices
Intelligence Index33.758.9
Coding Index77.4
Math Index
Agentic Index54
Speed & latency
Output speed (tok/s)8667
Time to first token1.01s120.38s
Time to first answer token24.40s120.38s
Benchmarks (Artificial Analysis)
GPQA Diamond84.8%94.1%
Humanity's Last Exam19.1%47.2%
SciCode42.6%56.1%
IFBench71.6%72.7%
AA-LCR (Long Context Reasoning)66.0%73.7%
Terminal-Bench Hard34.8%65.9%
Terminal-Bench 2.188.0%
τ²-Bench (Telecom)95.3%85.1%
τ³-Bench Banking33.0%
Design Arena (Elo)
Website1,249
UI components1,215
Data viz1,208
SVG1,197
3D1,228
Game dev1,235
Code categories1,240
Specs
Context window205K1.05M
Max output tokens197K128K
Input modalitiestextfile, image, text
TokenizerOtherGPT