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 SolQwen3.7 Plus
GPT-5.6 Sol

OpenAI

Qwen3.7 Plus

Alibaba (Qwen)

Pricing
Input $/1M$5.00$0.32
Output $/1M$30.00$1.28
Blended $/1M (3:1)$11.25$0.56
Cache read $/1M$0.50$0.064
Cache write $/1M$6.25$0.40
Quality indices
Intelligence Index58.939
Coding Index77.455.9
Math Index
Agentic Index5420.8
Speed & latency
Output speed (tok/s)6752
Time to first token120.38s1.68s
Time to first answer token120.38s40.30s
Benchmarks (Artificial Analysis)
GPQA Diamond94.1%90.0%
Humanity's Last Exam47.2%33.4%
SciCode56.1%45.5%
IFBench72.7%78.0%
AA-LCR (Long Context Reasoning)73.7%65.0%
Terminal-Bench Hard65.9%47.0%
Terminal-Bench 2.188.0%61.0%
τ²-Bench (Telecom)85.1%93.0%
τ³-Bench Banking33.0%17.9%
Design Arena (Elo)
Website1,289
UI components1,270
Data viz1,255
3D1,312
Game dev1,276
Code categories1,287
ASCII art1,191
Specs
Context window1.05M1M
Max output tokens128K66K
Input modalitiesfile, image, texttext, image
TokenizerGPTQwen