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 VL 32B Instruct
GPT-5.6 Sol

OpenAI

Qwen3 VL 32B Instruct

Alibaba (Qwen)

Pricing
Input $/1M$5.00$0.104
Output $/1M$30.00$0.416
Blended $/1M (3:1)$11.25$0.182
Cache read $/1M$0.50
Cache write $/1M$6.25
Quality indices
Intelligence Index58.911.1
Coding Index77.4
Math Index68.3
Agentic Index54
Speed & latency
Output speed (tok/s)6773
Time to first token120.38s1.12s
Time to first answer token120.38s1.12s
Benchmarks (Artificial Analysis)
MMLU-Pro79.1%
GPQA Diamond94.1%67.1%
Humanity's Last Exam47.2%6.3%
LiveCodeBench51.4%
SciCode56.1%30.1%
AIME 202568.3%
IFBench72.7%39.2%
AA-LCR (Long Context Reasoning)73.7%31.3%
Terminal-Bench Hard65.9%8.3%
Terminal-Bench 2.188.0%
τ²-Bench (Telecom)85.1%29.2%
τ³-Bench Banking33.0%
Specs
Context window1.05M131K
Max output tokens128K33K
Input modalitiesfile, image, texttext, image
TokenizerGPTQwen