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 Next
GPT-5.6 Sol

OpenAI

Qwen3 Coder Next

Alibaba (Qwen)

Pricing
Input $/1M$5.00$0.11
Output $/1M$30.00$0.80
Blended $/1M (3:1)$11.25$0.282
Cache read $/1M$0.50$0.07
Cache write $/1M$6.25
Quality indices
Intelligence Index58.921.1
Coding Index77.436.2
Math Index
Agentic Index548.8
Speed & latency
Output speed (tok/s)7096
Time to first token112.90s1.07s
Time to first answer token112.90s1.07s
Benchmarks (Artificial Analysis)
GPQA Diamond94.1%73.7%
Humanity's Last Exam47.2%9.3%
SciCode56.1%32.3%
IFBench72.7%35.2%
AA-LCR (Long Context Reasoning)73.7%40.0%
Terminal-Bench Hard65.9%18.2%
Terminal-Bench 2.188.0%38.2%
τ²-Bench (Telecom)85.1%79.5%
τ³-Bench Banking33.0%5.2%
Specs
Context window1.05M262K
Max output tokens128K262K
Input modalitiesfile, image, texttext
TokenizerGPTQwen