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 Coder 30B A3B Instruct
GPT-5.6 Sol

OpenAI

Qwen3 Coder 30B A3B Instruct

Alibaba (Qwen)

Pricing
Input $/1M$5.00$0.07
Output $/1M$30.00$0.27
Blended $/1M (3:1)$11.25$0.12
Cache read $/1M$0.50
Cache write $/1M$6.25
Quality indices
Intelligence Index58.913.6
Coding Index77.4
Math Index29
Agentic Index54
Speed & latency
Output speed (tok/s)67103
Time to first token120.38s1.61s
Time to first answer token120.38s1.61s
Benchmarks (Artificial Analysis)
MMLU-Pro70.6%
GPQA Diamond94.1%51.6%
Humanity's Last Exam47.2%4.0%
LiveCodeBench40.3%
SciCode56.1%27.8%
MATH-50089.3%
AIME29.7%
AIME 202529.0%
IFBench72.7%32.7%
AA-LCR (Long Context Reasoning)73.7%29.0%
Terminal-Bench Hard65.9%15.2%
Terminal-Bench 2.188.0%
τ²-Bench (Telecom)85.1%34.5%
τ³-Bench Banking33.0%
Design Arena (Elo)
Website1,115
UI components1,089
Data viz1,121
Specs
Context window1.05M262K
Max output tokens128K33K
Input modalitiesfile, image, texttext
TokenizerGPTQwen3