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 Next 80B A3B Instruct
GPT-5.6 Sol

OpenAI

Qwen3 Next 80B A3B Instruct

Alibaba (Qwen)

Pricing
Input $/1M$2.00$0.09
Output $/1M$10.00$1.10
Blended $/1M (3:1)$4.00$0.343
Cache read $/1M$0.20
Cache write $/1M$2.50
Quality indices
Intelligence Index479.6
Coding Index77.4
Math Index66.3
Agentic Index50.2
Speed & latency
Output speed (tok/s)65177
Time to first token64.46s0.99s
Time to first answer token64.46s0.99s
Benchmarks (Artificial Analysis)
MMLU-Pro81.9%
GPQA Diamond94.1%73.8%
Humanity's Last Exam49.5%7.6%
LiveCodeBench68.4%
SciCode57.1%
AIME 202566.3%
IFBench72.7%39.7%
AA-LCR (Long Context Reasoning)84.0%52.7%
Terminal-Bench Hard65.9%7.6%
Terminal-Bench 2.188.0%
τ²-Bench (Telecom)85.1%21.6%
τ³-Bench Banking44.3%
Specs
Context window1.05M262K
Max output tokens128K16K
Input modalitiesfile, image, texttext
TokenizerGPTQwen3