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 SolQwen3.5 397B A17B
GPT-5.6 Sol

OpenAI

Qwen3.5 397B A17B

Alibaba (Qwen)

Pricing
Input $/1M$2.00$0.55
Output $/1M$10.00$3.50
Blended $/1M (3:1)$4.00$1.29
Cache read $/1M$0.20$0.225
Cache write $/1M$2.50
Quality indices
Intelligence Index4718.4
Coding Index77.448.2
Math Index
Agentic Index50.28.3
Speed & latency
Output speed (tok/s)6587
Time to first token64.46s1.59s
Time to first answer token64.46s38.12s
Benchmarks (Artificial Analysis)
GPQA Diamond94.1%89.3%
Humanity's Last Exam49.5%29.0%
SciCode57.1%44.8%
IFBench72.7%78.8%
AA-LCR (Long Context Reasoning)84.0%77.3%
Terminal-Bench Hard65.9%40.9%
Terminal-Bench 2.188.0%51.3%
τ²-Bench (Telecom)85.1%95.6%
τ³-Bench Banking44.3%13.4%
Design Arena (Elo)
Website1,203
UI components1,179
Data viz1,190
SVG1,163
3D1,189
Game dev1,163
Code categories1,195
Specs
Context window1.05M262K
Max output tokens128K236K
Input modalitiesfile, image, texttext, image, video
TokenizerGPTQwen3