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.

GPT-5.6 SolQwen3 Max
GPT-5.6 Sol

OpenAI

Qwen3 Max

Alibaba (Qwen)

Pricing
Input $/1M$5.00$0.78
Output $/1M$30.00$3.90
Blended $/1M (3:1)$11.25$1.56
Cache read $/1M$0.50$0.156
Cache write $/1M$6.25$0.975
Quality indices
Intelligence Index58.924
Coding Index77.4
Math Index80.7
Agentic Index54
Speed & latency
Output speed (tok/s)6762
Time to first token120.38s1.77s
Time to first answer token120.38s1.77s
Benchmarks (Artificial Analysis)
MMLU-Pro84.1%
GPQA Diamond94.1%76.4%
Humanity's Last Exam47.2%11.1%
LiveCodeBench76.7%
SciCode56.1%38.3%
AIME 202580.7%
IFBench72.7%44.1%
AA-LCR (Long Context Reasoning)73.7%46.7%
Terminal-Bench Hard65.9%20.5%
Terminal-Bench 2.188.0%
τ²-Bench (Telecom)85.1%74.3%
τ³-Bench Banking33.0%
Design Arena (Elo)
Website1,146
UI components1,119
Data viz1,141
SVG1,058
3D1,132
Game dev1,153
Code categories1,143
ASCII art1,170
Specs
Context window1.05M262K
Max output tokens128K33K
Input modalitiesfile, image, texttext
TokenizerGPTQwen3