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.

Ling 3.0 FlashGPT-5.6 Sol
Ling 3.0 Flash

Inclusionai

GPT-5.6 Sol

OpenAI

Pricing
Input $/1M$0.021$2.00
Output $/1M$0.063$10.00
Blended $/1M (3:1)$0.032$4.00
Cache read $/1M$0.0042$0.20
Cache write $/1M$2.50
Quality indices
Intelligence Index24.947
Coding Index50.677.4
Math Index
Agentic Index50.2
Speed & latency
Output speed (tok/s)35465
Time to first token1.64s64.46s
Time to first answer token7.30s64.46s
Benchmarks (Artificial Analysis)
GPQA Diamond85.5%94.1%
Humanity's Last Exam23.7%49.5%
SciCode42.0%57.1%
IFBench72.7%
AA-LCR (Long Context Reasoning)73.0%84.0%
Terminal-Bench Hard65.9%
Terminal-Bench 2.155.4%88.0%
τ²-Bench (Telecom)85.1%
τ³-Bench Banking27.2%44.3%
Specs
Context window262K1.05M
Max output tokens33K128K
Input modalitiestextfile, image, text
TokenizerOtherGPT