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 235B A22B Instruct 2507
GPT-5.6 Sol

OpenAI

Qwen3 235B A22B Instruct 2507

Alibaba (Qwen)

Pricing
Input $/1M$5.00$0.09
Output $/1M$30.00$0.55
Blended $/1M (3:1)$11.25$0.205
Cache read $/1M$0.50
Cache write $/1M$6.25
Quality indices
Intelligence Index58.918.2
Coding Index77.4
Math Index71.7
Agentic Index54
Speed & latency
Output speed (tok/s)6774
Time to first token120.38s1.12s
Time to first answer token120.38s1.12s
Benchmarks (Artificial Analysis)
MMLU-Pro82.8%
GPQA Diamond94.1%75.3%
Humanity's Last Exam47.2%10.6%
LiveCodeBench52.4%
SciCode56.1%36.0%
MATH-50098.0%
AIME71.7%
AIME 202571.7%
IFBench72.7%46.1%
AA-LCR (Long Context Reasoning)73.7%31.2%
Terminal-Bench Hard65.9%15.2%
Terminal-Bench 2.188.0%
τ²-Bench (Telecom)85.1%33.3%
τ³-Bench Banking33.0%
Design Arena (Elo)
Website1,085
UI components1,009
Data viz1,095
3D1,053
Game dev1,010
Code categories1,072
Specs
Context window1.05M262K
Max output tokens128K16K
Input modalitiesfile, image, texttext
TokenizerGPTQwen3