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.

Llama 4 MaverickGPT-5.6 Sol
Llama 4 Maverick

Meta

GPT-5.6 Sol

OpenAI

Pricing
Input $/1M$0.20$5.00
Output $/1M$0.80$30.00
Blended $/1M (3:1)$0.35$11.25
Cache read $/1M$0.50
Cache write $/1M$6.25
Quality indices
Intelligence Index14.358.9
Coding Index16.377.4
Math Index19.3
Agentic Index1.354
Speed & latency
Output speed (tok/s)11067
Time to first token0.59s120.38s
Time to first answer token0.59s120.38s
Benchmarks (Artificial Analysis)
MMLU-Pro80.9%
GPQA Diamond67.1%94.1%
Humanity's Last Exam4.8%47.2%
LiveCodeBench39.7%
SciCode33.1%56.1%
MATH-50088.9%
AIME39.0%
AIME 202519.3%
IFBench43.0%72.7%
AA-LCR (Long Context Reasoning)46.0%73.7%
Terminal-Bench Hard6.8%65.9%
Terminal-Bench 2.17.9%88.0%
τ²-Bench (Telecom)17.8%85.1%
τ³-Bench Banking3.9%33.0%
Design Arena (Elo)
Website898
UI components942
Data viz919
3D958
Game dev896
Code categories913
Specs
Context window1.05M1.05M
Max output tokens16K128K
Input modalitiestext, imagefile, image, text
TokenizerLlama4GPT