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 8B Instruct
GPT-5.6 Sol

OpenAI

Qwen3 VL 8B Instruct

Alibaba (Qwen)

Pricing
Input $/1M$5.00$0.117
Output $/1M$30.00$0.455
Blended $/1M (3:1)$11.25$0.202
Cache read $/1M$0.50
Cache write $/1M$6.25
Quality indices
Intelligence Index58.98.4
Coding Index77.4
Math Index27.3
Agentic Index54
Speed & latency
Output speed (tok/s)67141
Time to first token120.38s0.90s
Time to first answer token120.38s0.90s
Benchmarks (Artificial Analysis)
MMLU-Pro68.6%
GPQA Diamond94.1%42.7%
Humanity's Last Exam47.2%2.9%
LiveCodeBench33.2%
SciCode56.1%17.4%
AIME 202527.3%
IFBench72.7%32.3%
AA-LCR (Long Context Reasoning)73.7%15.3%
Terminal-Bench Hard65.9%2.3%
Terminal-Bench 2.188.0%
τ²-Bench (Telecom)85.1%29.2%
τ³-Bench Banking33.0%
Specs
Context window1.05M262K
Max output tokens128K33K
Input modalitiesfile, image, textimage, text
TokenizerGPTQwen3